Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 26 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6103. Min Range: -6.6103
Max Act: 6.6103. Min Act: -0.1700
Data Index: 5916184 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6103. Min Range: -6.6103
Max Act: 6.3916. Min Act: -0.1700
Data Index: 827034 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6103. Min Range: -6.6103
Max Act: 6.2978. Min Act: -0.1700
Data Index: 5035459 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6103. Min Range: -6.6103
Max Act: 6.2666. Min Act: -0.1700
Data Index: 2975030 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6103. Min Range: -6.6103
Max Act: 6.2978. Min Act: -0.1700
Data Index: 5857992 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6103. Min Range: -6.6103
Max Act: 6.1728. Min Act: -0.1700
Data Index: 7795898 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6103. Min Range: -6.6103
Max Act: 6.1416. Min Act: -0.1700
Data Index: 1512471 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6103. Min Range: -6.6103
Max Act: 6.1416. Min Act: -0.1700
Data Index: 2529602 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6103. Min Range: -6.6103
Max Act: 6.0791. Min Act: -0.1700
Data Index: 7684690 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6103. Min Range: -6.6103
Max Act: 6.0791. Min Act: -0.1700
Data Index: 1690180 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6103. Min Range: -6.6103
Max Act: 6.0791. Min Act: -0.1700
Data Index: 827029 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6103. Min Range: -6.6103
Max Act: 6.0791. Min Act: -0.1700
Data Index: 2300261 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6103. Min Range: -6.6103
Max Act: 6.0791. Min Act: -0.1700
Data Index: 4460575 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6103. Min Range: -6.6103
Max Act: 6.0478. Min Act: -0.1700
Data Index: 5505097 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6103. Min Range: -6.6103
Max Act: 6.0166. Min Act: -0.1700
Data Index: 7006722 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6103. Min Range: -6.6103
Max Act: 6.0478. Min Act: -0.1700
Data Index: 7759898 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6103. Min Range: -6.6103
Max Act: 6.0166. Min Act: -0.1700
Data Index: 827033 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6103. Min Range: -6.6103
Max Act: 6.0166. Min Act: -0.1700
Data Index: 4285046 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6103. Min Range: -6.6103
Max Act: 6.0166. Min Act: -0.1700
Data Index: 4262022 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6103. Min Range: -6.6103
Max Act: 6.0166. Min Act: -0.1700
Data Index: 3511206 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19