Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4041 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6964. Min Range: -1.6964
Max Act: 1.6964. Min Act: -0.1700
Data Index: 8257995 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6964. Min Range: -1.6964
Max Act: 1.6703. Min Act: -0.1700
Data Index: 4089114 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6964. Min Range: -1.6964
Max Act: 1.6703. Min Act: -0.1699
Data Index: 1948664 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6964. Min Range: -1.6964
Max Act: 1.6703. Min Act: -0.1695
Data Index: 5355063 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6964. Min Range: -1.6964
Max Act: 1.6529. Min Act: -0.1696
Data Index: 5571654 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6964. Min Range: -1.6964
Max Act: 1.6442. Min Act: -0.1700
Data Index: 1882046 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6964. Min Range: -1.6964
Max Act: 1.6529. Min Act: -0.1700
Data Index: 3109055 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6964. Min Range: -1.6964
Max Act: 1.6355. Min Act: -0.1699
Data Index: 1602076 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6964. Min Range: -1.6964
Max Act: 1.6268. Min Act: -0.1700
Data Index: 7346889 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6964. Min Range: -1.6964
Max Act: 1.6268. Min Act: -0.1700
Data Index: 4342336 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6964. Min Range: -1.6964
Max Act: 1.6268. Min Act: -0.1700
Data Index: 4219334 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6964. Min Range: -1.6964
Max Act: 1.6268. Min Act: -0.1700
Data Index: 1964341 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6964. Min Range: -1.6964
Max Act: 1.6268. Min Act: -0.1700
Data Index: 7038772 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6964. Min Range: -1.6964
Max Act: 1.6268. Min Act: -0.1698
Data Index: 4089679 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6964. Min Range: -1.6964
Max Act: 1.6181. Min Act: -0.1700
Data Index: 8775293 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6964. Min Range: -1.6964
Max Act: 1.6094. Min Act: -0.1700
Data Index: 4303954 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6964. Min Range: -1.6964
Max Act: 1.6181. Min Act: -0.1700
Data Index: 7311110 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6964. Min Range: -1.6964
Max Act: 1.6094. Min Act: -0.1699
Data Index: 3978652 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6964. Min Range: -1.6964
Max Act: 1.6094. Min Act: -0.1700
Data Index: 2519429 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6964. Min Range: -1.6964
Max Act: 1.5919. Min Act: -0.1700
Data Index: 1268942 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19