Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3112 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5105. Min Range: -10.5105
Max Act: 10.5105. Min Act: -0.1700
Data Index: 1214383 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5105. Min Range: -10.5105
Max Act: 10.5105. Min Act: -0.1700
Data Index: 4862753 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5105. Min Range: -10.5105
Max Act: 10.3855. Min Act: -0.1700
Data Index: 2201674 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5105. Min Range: -10.5105
Max Act: 10.3855. Min Act: -0.1700
Data Index: 996479 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5105. Min Range: -10.5105
Max Act: 10.3855. Min Act: -0.1700
Data Index: 1512091 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5105. Min Range: -10.5105
Max Act: 10.4480. Min Act: -0.1700
Data Index: 4448466 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5105. Min Range: -10.5105
Max Act: 10.3230. Min Act: -0.1700
Data Index: 8689785 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5105. Min Range: -10.5105
Max Act: 10.1980. Min Act: -0.1700
Data Index: 2824594 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5105. Min Range: -10.5105
Max Act: 10.1980. Min Act: -0.1700
Data Index: 2284376 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5105. Min Range: -10.5105
Max Act: 10.1980. Min Act: -0.1700
Data Index: 6493794 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5105. Min Range: -10.5105
Max Act: 10.1980. Min Act: -0.1700
Data Index: 6796868 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5105. Min Range: -10.5105
Max Act: 10.1355. Min Act: -0.1700
Data Index: 5180958 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5105. Min Range: -10.5105
Max Act: 10.1355. Min Act: -0.1700
Data Index: 6137438 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5105. Min Range: -10.5105
Max Act: 10.1355. Min Act: -0.1700
Data Index: 2689688 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5105. Min Range: -10.5105
Max Act: 10.1355. Min Act: -0.1700
Data Index: 7512022 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5105. Min Range: -10.5105
Max Act: 10.1355. Min Act: -0.1700
Data Index: 7695059 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5105. Min Range: -10.5105
Max Act: 10.0730. Min Act: -0.1700
Data Index: 6497240 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5105. Min Range: -10.5105
Max Act: 10.0730. Min Act: -0.1700
Data Index: 7354221 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5105. Min Range: -10.5105
Max Act: 10.1355. Min Act: -0.1700
Data Index: 1307250 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5105. Min Range: -10.5105
Max Act: 10.1355. Min Act: -0.1700
Data Index: 1591980 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19