Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2673 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7151. Min Range: -4.7151
Max Act: 4.7151. Min Act: -0.1700
Data Index: 4263285 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7151. Min Range: -4.7151
Max Act: 4.6213. Min Act: -0.1700
Data Index: 2537818 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7151. Min Range: -4.7151
Max Act: 4.5588. Min Act: -0.1700
Data Index: 3333584 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7151. Min Range: -4.7151
Max Act: 4.5588. Min Act: -0.1700
Data Index: 6091012 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7151. Min Range: -4.7151
Max Act: 4.5276. Min Act: -0.1700
Data Index: 400241 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7151. Min Range: -4.7151
Max Act: 4.4963. Min Act: -0.1700
Data Index: 3251984 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7151. Min Range: -4.7151
Max Act: 4.4963. Min Act: -0.1700
Data Index: 4082450 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7151. Min Range: -4.7151
Max Act: 4.4963. Min Act: -0.1700
Data Index: 40827 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7151. Min Range: -4.7151
Max Act: 4.4651. Min Act: -0.1700
Data Index: 1412911 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7151. Min Range: -4.7151
Max Act: 4.4651. Min Act: -0.1700
Data Index: 8649349 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7151. Min Range: -4.7151
Max Act: 4.4651. Min Act: -0.1700
Data Index: 4190423 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7151. Min Range: -4.7151
Max Act: 4.4338. Min Act: -0.1700
Data Index: 897123 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7151. Min Range: -4.7151
Max Act: 4.4026. Min Act: -0.1700
Data Index: 8668216 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7151. Min Range: -4.7151
Max Act: 4.4026. Min Act: -0.1700
Data Index: 4919609 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7151. Min Range: -4.7151
Max Act: 4.4026. Min Act: -0.1700
Data Index: 850140 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7151. Min Range: -4.7151
Max Act: 4.4026. Min Act: -0.1700
Data Index: 2626776 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7151. Min Range: -4.7151
Max Act: 4.4026. Min Act: -0.1700
Data Index: 1275225 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7151. Min Range: -4.7151
Max Act: 4.3713. Min Act: -0.1700
Data Index: 94646 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7151. Min Range: -4.7151
Max Act: 4.3713. Min Act: -0.1700
Data Index: 8254175 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7151. Min Range: -4.7151
Max Act: 4.3401. Min Act: -0.1700
Data Index: 6308249 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19