Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3298 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.6149. Min Act: -0.1700
Data Index: 4850835 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.5993. Min Act: -0.1700
Data Index: 740459 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.5367. Min Act: -0.1700
Data Index: 4523967 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.5367. Min Act: -0.1700
Data Index: 5532885 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.5367. Min Act: -0.1700
Data Index: 4495327 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.4897. Min Act: -0.1700
Data Index: 6455428 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.4740. Min Act: -0.1700
Data Index: 5092110 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.4427. Min Act: -0.1700
Data Index: 3649421 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.4583. Min Act: -0.1700
Data Index: 5664163 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.4270. Min Act: -0.1700
Data Index: 6075692 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.3956. Min Act: -0.1700
Data Index: 913076 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.4113. Min Act: -0.1700
Data Index: 4198930 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.4113. Min Act: -0.1700
Data Index: 2900976 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.3800. Min Act: -0.1700
Data Index: 347718 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.3800. Min Act: -0.1700
Data Index: 7089661 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.3800. Min Act: -0.1700
Data Index: 4735345 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.3643. Min Act: -0.1700
Data Index: 4559321 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.3643. Min Act: -0.1700
Data Index: 8757748 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.3643. Min Act: -0.1700
Data Index: 2208299 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6149. Min Range: -3.6149
Max Act: 3.3486. Min Act: -0.1700
Data Index: 3674064 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #19