Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6149 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9657. Min Range: -7.9657
Max Act: 7.9657. Min Act: -0.1700
Data Index: 1270786 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9657. Min Range: -7.9657
Max Act: 7.9657. Min Act: -0.1700
Data Index: 8778169 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9657. Min Range: -7.9657
Max Act: 7.7782. Min Act: -0.1700
Data Index: 8649879 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9657. Min Range: -7.9657
Max Act: 7.7157. Min Act: -0.1700
Data Index: 2450219 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9657. Min Range: -7.9657
Max Act: 7.7157. Min Act: -0.1700
Data Index: 5010649 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9657. Min Range: -7.9657
Max Act: 7.4970. Min Act: -0.1700
Data Index: 5107090 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9657. Min Range: -7.9657
Max Act: 7.4657. Min Act: -0.1700
Data Index: 6875765 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9657. Min Range: -7.9657
Max Act: 7.4657. Min Act: -0.1700
Data Index: 5760076 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9657. Min Range: -7.9657
Max Act: 7.4345. Min Act: -0.1700
Data Index: 3920902 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9657. Min Range: -7.9657
Max Act: 7.4032. Min Act: -0.1700
Data Index: 7713476 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9657. Min Range: -7.9657
Max Act: 7.3720. Min Act: -0.1700
Data Index: 5041711 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9657. Min Range: -7.9657
Max Act: 7.3407. Min Act: -0.1700
Data Index: 5465478 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9657. Min Range: -7.9657
Max Act: 7.3407. Min Act: -0.1700
Data Index: 2695382 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9657. Min Range: -7.9657
Max Act: 7.3407. Min Act: -0.1700
Data Index: 3407759 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9657. Min Range: -7.9657
Max Act: 7.3407. Min Act: -0.1700
Data Index: 2359971 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9657. Min Range: -7.9657
Max Act: 7.3407. Min Act: -0.1700
Data Index: 2373214 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9657. Min Range: -7.9657
Max Act: 7.3407. Min Act: -0.1700
Data Index: 3351084 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9657. Min Range: -7.9657
Max Act: 7.3095. Min Act: -0.1700
Data Index: 1882597 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9657. Min Range: -7.9657
Max Act: 7.3095. Min Act: -0.1700
Data Index: 4110130 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9657. Min Range: -7.9657
Max Act: 7.2782. Min Act: -0.1700
Data Index: 3061084 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19