Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3505 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1070. Min Range: -5.1070
Max Act: 5.1070. Min Act: -0.1700
Data Index: 5450442 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1070. Min Range: -5.1070
Max Act: 5.0445. Min Act: -0.1700
Data Index: 4511085 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.9195. Min Act: -0.1700
Data Index: 4211586 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.8570. Min Act: -0.1700
Data Index: 6946950 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.8570. Min Act: -0.1700
Data Index: 4511817 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.8570. Min Act: -0.1700
Data Index: 143881 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.8570. Min Act: -0.1700
Data Index: 8649955 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.8570. Min Act: -0.1700
Data Index: 4338243 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.8257. Min Act: -0.1700
Data Index: 446767 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.7945. Min Act: -0.1700
Data Index: 8704377 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.7945. Min Act: -0.1700
Data Index: 2762456 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.7945. Min Act: -0.1700
Data Index: 5738132 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.7945. Min Act: -0.1700
Data Index: 4160695 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.7632. Min Act: -0.1700
Data Index: 7176990 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.7945. Min Act: -0.1700
Data Index: 7041949 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.7320. Min Act: -0.1700
Data Index: 3401126 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.7632. Min Act: -0.1700
Data Index: 7565284 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.7632. Min Act: -0.1700
Data Index: 3479140 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.7632. Min Act: -0.1700
Data Index: 7829949 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1070. Min Range: -5.1070
Max Act: 4.7632. Min Act: -0.1700
Data Index: 6652143 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19