Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 322 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7191. Min Range: -5.7191
Max Act: 5.7191. Min Act: -0.1700
Data Index: 7650222 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7191. Min Range: -5.7191
Max Act: 5.5628. Min Act: -0.1700
Data Index: 2766254 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7191. Min Range: -5.7191
Max Act: 5.5316. Min Act: -0.1700
Data Index: 2999470 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7191. Min Range: -5.7191
Max Act: 5.5316. Min Act: -0.1700
Data Index: 1787500 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7191. Min Range: -5.7191
Max Act: 5.5003. Min Act: -0.1700
Data Index: 7837578 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7191. Min Range: -5.7191
Max Act: 5.4691. Min Act: -0.1700
Data Index: 6134332 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7191. Min Range: -5.7191
Max Act: 5.4378. Min Act: -0.1700
Data Index: 6899158 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7191. Min Range: -5.7191
Max Act: 5.3753. Min Act: -0.1700
Data Index: 6705457 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7191. Min Range: -5.7191
Max Act: 5.3441. Min Act: -0.1700
Data Index: 5573273 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7191. Min Range: -5.7191
Max Act: 5.3753. Min Act: -0.1700
Data Index: 8489236 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7191. Min Range: -5.7191
Max Act: 5.3441. Min Act: -0.1700
Data Index: 650509 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7191. Min Range: -5.7191
Max Act: 5.3128. Min Act: -0.1700
Data Index: 7877689 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7191. Min Range: -5.7191
Max Act: 5.2816. Min Act: -0.1700
Data Index: 2347058 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7191. Min Range: -5.7191
Max Act: 5.2816. Min Act: -0.1700
Data Index: 6498055 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7191. Min Range: -5.7191
Max Act: 5.2503. Min Act: -0.1700
Data Index: 1830170 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7191. Min Range: -5.7191
Max Act: 5.2503. Min Act: -0.1700
Data Index: 1714161 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7191. Min Range: -5.7191
Max Act: 5.2503. Min Act: -0.1700
Data Index: 7454560 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7191. Min Range: -5.7191
Max Act: 5.2503. Min Act: -0.1700
Data Index: 3297523 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7191. Min Range: -5.7191
Max Act: 5.2503. Min Act: -0.1700
Data Index: 7058922 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7191. Min Range: -5.7191
Max Act: 5.2503. Min Act: -0.1700
Data Index: 473418 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19