Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1645 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4511. Min Range: -5.4511
Max Act: 5.4511. Min Act: -0.1700
Data Index: 2269404 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4511. Min Range: -5.4511
Max Act: 5.4511. Min Act: -0.1700
Data Index: 6745600 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4511. Min Range: -5.4511
Max Act: 5.4199. Min Act: -0.1700
Data Index: 6313405 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4511. Min Range: -5.4511
Max Act: 5.3574. Min Act: -0.1700
Data Index: 8479125 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4511. Min Range: -5.4511
Max Act: 5.2949. Min Act: -0.1700
Data Index: 5419275 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4511. Min Range: -5.4511
Max Act: 5.2949. Min Act: -0.1699
Data Index: 716189 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4511. Min Range: -5.4511
Max Act: 5.2324. Min Act: -0.1700
Data Index: 8555290 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4511. Min Range: -5.4511
Max Act: 5.2324. Min Act: -0.1700
Data Index: 74917 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4511. Min Range: -5.4511
Max Act: 5.2011. Min Act: -0.1700
Data Index: 145998 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4511. Min Range: -5.4511
Max Act: 5.2011. Min Act: -0.1700
Data Index: 4730443 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4511. Min Range: -5.4511
Max Act: 5.2011. Min Act: -0.1700
Data Index: 150512 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4511. Min Range: -5.4511
Max Act: 5.1699. Min Act: -0.1700
Data Index: 457093 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4511. Min Range: -5.4511
Max Act: 5.1699. Min Act: -0.1700
Data Index: 5519144 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4511. Min Range: -5.4511
Max Act: 5.1386. Min Act: -0.1700
Data Index: 3954642 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4511. Min Range: -5.4511
Max Act: 5.1074. Min Act: -0.1700
Data Index: 8326006 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4511. Min Range: -5.4511
Max Act: 5.1074. Min Act: -0.1700
Data Index: 1306253 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4511. Min Range: -5.4511
Max Act: 5.1074. Min Act: -0.1700
Data Index: 1484578 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4511. Min Range: -5.4511
Max Act: 5.0761. Min Act: -0.1700
Data Index: 8717366 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4511. Min Range: -5.4511
Max Act: 5.1074. Min Act: -0.1700
Data Index: 6452101 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4511. Min Range: -5.4511
Max Act: 5.1074. Min Act: -0.1700
Data Index: 3114350 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19