Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2952 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4230. Min Range: -6.4230
Max Act: 6.4230. Min Act: -0.1700
Data Index: 4011409 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4230. Min Range: -6.4230
Max Act: 6.4230. Min Act: -0.1700
Data Index: 8012582 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4230. Min Range: -6.4230
Max Act: 6.2980. Min Act: -0.1700
Data Index: 8094633 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4230. Min Range: -6.4230
Max Act: 6.2668. Min Act: -0.1700
Data Index: 7809514 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4230. Min Range: -6.4230
Max Act: 6.2668. Min Act: -0.1700
Data Index: 4598721 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4230. Min Range: -6.4230
Max Act: 6.2355. Min Act: -0.1700
Data Index: 5352449 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4230. Min Range: -6.4230
Max Act: 6.2668. Min Act: -0.1700
Data Index: 966886 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4230. Min Range: -6.4230
Max Act: 6.2043. Min Act: -0.1700
Data Index: 900387 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4230. Min Range: -6.4230
Max Act: 6.1418. Min Act: -0.1700
Data Index: 6792317 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4230. Min Range: -6.4230
Max Act: 6.1105. Min Act: -0.1700
Data Index: 3737644 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4230. Min Range: -6.4230
Max Act: 6.0480. Min Act: -0.1700
Data Index: 7114998 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4230. Min Range: -6.4230
Max Act: 6.0168. Min Act: -0.1700
Data Index: 30222 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4230. Min Range: -6.4230
Max Act: 5.9855. Min Act: -0.1700
Data Index: 7839699 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4230. Min Range: -6.4230
Max Act: 6.0168. Min Act: -0.1700
Data Index: 7967099 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4230. Min Range: -6.4230
Max Act: 5.9855. Min Act: -0.1700
Data Index: 2650358 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4230. Min Range: -6.4230
Max Act: 5.9543. Min Act: -0.1700
Data Index: 3592691 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4230. Min Range: -6.4230
Max Act: 5.9543. Min Act: -0.1700
Data Index: 4873292 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4230. Min Range: -6.4230
Max Act: 5.9543. Min Act: -0.1700
Data Index: 5333896 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4230. Min Range: -6.4230
Max Act: 5.9543. Min Act: -0.1700
Data Index: 2798076 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4230. Min Range: -6.4230
Max Act: 5.9230. Min Act: -0.1700
Data Index: 6639661 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #19