Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3198 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1148. Min Range: -9.1148
Max Act: 9.1148. Min Act: -0.1700
Data Index: 429625 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1148. Min Range: -9.1148
Max Act: 9.0523. Min Act: -0.1700
Data Index: 6194574 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1148. Min Range: -9.1148
Max Act: 8.8023. Min Act: -0.1700
Data Index: 349036 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1148. Min Range: -9.1148
Max Act: 8.7398. Min Act: -0.1700
Data Index: 8286647 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1148. Min Range: -9.1148
Max Act: 8.6773. Min Act: -0.1700
Data Index: 3450285 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1148. Min Range: -9.1148
Max Act: 8.6148. Min Act: -0.1700
Data Index: 4686236 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1148. Min Range: -9.1148
Max Act: 8.6148. Min Act: -0.1700
Data Index: 4423122 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1148. Min Range: -9.1148
Max Act: 8.4898. Min Act: -0.1700
Data Index: 8158475 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1148. Min Range: -9.1148
Max Act: 8.4898. Min Act: -0.1700
Data Index: 2325226 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1148. Min Range: -9.1148
Max Act: 8.5523. Min Act: -0.1700
Data Index: 1573887 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1148. Min Range: -9.1148
Max Act: 8.4898. Min Act: -0.1700
Data Index: 1629017 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1148. Min Range: -9.1148
Max Act: 8.5523. Min Act: -0.1700
Data Index: 7971395 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1148. Min Range: -9.1148
Max Act: 8.4273. Min Act: -0.1700
Data Index: 5003946 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1148. Min Range: -9.1148
Max Act: 8.4273. Min Act: -0.1700
Data Index: 2770673 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1148. Min Range: -9.1148
Max Act: 8.4273. Min Act: -0.1700
Data Index: 587198 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1148. Min Range: -9.1148
Max Act: 8.4273. Min Act: -0.1700
Data Index: 5591203 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1148. Min Range: -9.1148
Max Act: 8.4273. Min Act: -0.1700
Data Index: 6795162 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1148. Min Range: -9.1148
Max Act: 8.4273. Min Act: -0.1700
Data Index: 676350 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1148. Min Range: -9.1148
Max Act: 8.3648. Min Act: -0.1700
Data Index: 1985094 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1148. Min Range: -9.1148
Max Act: 8.3648. Min Act: -0.1700
Data Index: 4747230 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19