Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2950 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3169. Min Range: -5.3169
Max Act: 5.3169. Min Act: -0.1700
Data Index: 7323514 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3169. Min Range: -5.3169
Max Act: 5.0669. Min Act: -0.1700
Data Index: 7475379 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3169. Min Range: -5.3169
Max Act: 5.0044. Min Act: -0.1700
Data Index: 7323513 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3169. Min Range: -5.3169
Max Act: 4.9106. Min Act: -0.1700
Data Index: 7119174 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3169. Min Range: -5.3169
Max Act: 4.8169. Min Act: -0.1700
Data Index: 5578001 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3169. Min Range: -5.3169
Max Act: 4.7856. Min Act: -0.1700
Data Index: 8383507 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3169. Min Range: -5.3169
Max Act: 4.7544. Min Act: -0.1700
Data Index: 4158077 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3169. Min Range: -5.3169
Max Act: 4.7231. Min Act: -0.1700
Data Index: 7608287 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3169. Min Range: -5.3169
Max Act: 4.7231. Min Act: -0.1700
Data Index: 8614919 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3169. Min Range: -5.3169
Max Act: 4.7231. Min Act: -0.1700
Data Index: 3292882 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3169. Min Range: -5.3169
Max Act: 4.6919. Min Act: -0.1700
Data Index: 5726394 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3169. Min Range: -5.3169
Max Act: 4.6919. Min Act: -0.1700
Data Index: 3503021 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3169. Min Range: -5.3169
Max Act: 4.6919. Min Act: -0.1700
Data Index: 1645196 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3169. Min Range: -5.3169
Max Act: 4.6919. Min Act: -0.1700
Data Index: 3551863 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3169. Min Range: -5.3169
Max Act: 4.6919. Min Act: -0.1700
Data Index: 4913504 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3169. Min Range: -5.3169
Max Act: 4.6606. Min Act: -0.1700
Data Index: 4726565 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3169. Min Range: -5.3169
Max Act: 4.6606. Min Act: -0.1700
Data Index: 966864 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3169. Min Range: -5.3169
Max Act: 4.6606. Min Act: -0.1700
Data Index: 3551864 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3169. Min Range: -5.3169
Max Act: 4.6606. Min Act: -0.1700
Data Index: 2383560 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3169. Min Range: -5.3169
Max Act: 4.6606. Min Act: -0.1700
Data Index: 3765997 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19