Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3663 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6490. Min Range: -7.6490
Max Act: 7.6490. Min Act: -0.1700
Data Index: 3908038 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6490. Min Range: -7.6490
Max Act: 7.0240. Min Act: -0.1700
Data Index: 5934204 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6490. Min Range: -7.6490
Max Act: 6.9927. Min Act: -0.1700
Data Index: 1914149 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6490. Min Range: -7.6490
Max Act: 6.9302. Min Act: -0.1700
Data Index: 7230161 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6490. Min Range: -7.6490
Max Act: 6.8365. Min Act: -0.1700
Data Index: 5732684 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6490. Min Range: -7.6490
Max Act: 6.8052. Min Act: -0.1700
Data Index: 373917 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6490. Min Range: -7.6490
Max Act: 6.8365. Min Act: -0.1700
Data Index: 3633430 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6490. Min Range: -7.6490
Max Act: 6.8365. Min Act: -0.1700
Data Index: 4259351 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6490. Min Range: -7.6490
Max Act: 6.7740. Min Act: -0.1700
Data Index: 5531655 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6490. Min Range: -7.6490
Max Act: 6.7115. Min Act: -0.1700
Data Index: 626425 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6490. Min Range: -7.6490
Max Act: 6.7115. Min Act: -0.1700
Data Index: 1600142 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6490. Min Range: -7.6490
Max Act: 6.6802. Min Act: -0.1700
Data Index: 6652864 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6490. Min Range: -7.6490
Max Act: 6.6802. Min Act: -0.1700
Data Index: 2120126 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6490. Min Range: -7.6490
Max Act: 6.6490. Min Act: -0.1700
Data Index: 4422232 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6490. Min Range: -7.6490
Max Act: 6.6490. Min Act: -0.1700
Data Index: 347915 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6490. Min Range: -7.6490
Max Act: 6.6177. Min Act: -0.1700
Data Index: 86579 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6490. Min Range: -7.6490
Max Act: 6.5552. Min Act: -0.1700
Data Index: 3368262 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6490. Min Range: -7.6490
Max Act: 6.5240. Min Act: -0.1700
Data Index: 4237028 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6490. Min Range: -7.6490
Max Act: 6.5240. Min Act: -0.1700
Data Index: 3752777 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6490. Min Range: -7.6490
Max Act: 6.5240. Min Act: -0.1700
Data Index: 231778 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19