Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2658 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8168. Min Range: -4.8168
Max Act: 4.8168. Min Act: -0.1700
Data Index: 8521416 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8168. Min Range: -4.8168
Max Act: 4.6293. Min Act: -0.1700
Data Index: 4519485 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8168. Min Range: -4.8168
Max Act: 4.5043. Min Act: -0.1700
Data Index: 8794146 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8168. Min Range: -4.8168
Max Act: 4.4731. Min Act: -0.1700
Data Index: 1069639 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8168. Min Range: -4.8168
Max Act: 4.4418. Min Act: -0.1700
Data Index: 8242945 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8168. Min Range: -4.8168
Max Act: 4.4731. Min Act: -0.1700
Data Index: 79113 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8168. Min Range: -4.8168
Max Act: 4.4418. Min Act: -0.1700
Data Index: 4758748 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8168. Min Range: -4.8168
Max Act: 4.4106. Min Act: -0.1700
Data Index: 7581902 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8168. Min Range: -4.8168
Max Act: 4.4418. Min Act: -0.1700
Data Index: 3836921 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8168. Min Range: -4.8168
Max Act: 4.4418. Min Act: -0.1700
Data Index: 3056180 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8168. Min Range: -4.8168
Max Act: 4.4418. Min Act: -0.1700
Data Index: 2517651 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8168. Min Range: -4.8168
Max Act: 4.4418. Min Act: -0.1700
Data Index: 1570074 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8168. Min Range: -4.8168
Max Act: 4.4106. Min Act: -0.1700
Data Index: 6335150 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8168. Min Range: -4.8168
Max Act: 4.4106. Min Act: -0.1700
Data Index: 6335148 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8168. Min Range: -4.8168
Max Act: 4.4106. Min Act: -0.1700
Data Index: 4896832 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8168. Min Range: -4.8168
Max Act: 4.4106. Min Act: -0.1700
Data Index: 3361751 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8168. Min Range: -4.8168
Max Act: 4.4106. Min Act: -0.1700
Data Index: 4670946 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8168. Min Range: -4.8168
Max Act: 4.4418. Min Act: -0.1700
Data Index: 4747823 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8168. Min Range: -4.8168
Max Act: 4.3793. Min Act: -0.1700
Data Index: 3836917 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8168. Min Range: -4.8168
Max Act: 4.3793. Min Act: -0.1700
Data Index: 5796304 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19