Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3993 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4387. Min Range: -5.4387
Max Act: 5.4075. Min Act: -0.1700
Data Index: 6858269 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4387. Min Range: -5.4387
Max Act: 5.4387. Min Act: -0.1700
Data Index: 470837 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4387. Min Range: -5.4387
Max Act: 5.4387. Min Act: -0.1700
Data Index: 4701902 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4387. Min Range: -5.4387
Max Act: 5.3450. Min Act: -0.1700
Data Index: 8547800 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4387. Min Range: -5.4387
Max Act: 5.3450. Min Act: -0.1700
Data Index: 699726 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4387. Min Range: -5.4387
Max Act: 5.3762. Min Act: -0.1700
Data Index: 1797076 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4387. Min Range: -5.4387
Max Act: 5.3137. Min Act: -0.1700
Data Index: 5071914 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4387. Min Range: -5.4387
Max Act: 5.3450. Min Act: -0.1700
Data Index: 4904715 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4387. Min Range: -5.4387
Max Act: 5.3450. Min Act: -0.1700
Data Index: 2491548 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4387. Min Range: -5.4387
Max Act: 5.3762. Min Act: -0.1700
Data Index: 1289490 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4387. Min Range: -5.4387
Max Act: 5.3137. Min Act: -0.1700
Data Index: 971233 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4387. Min Range: -5.4387
Max Act: 5.3450. Min Act: -0.1700
Data Index: 2132376 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4387. Min Range: -5.4387
Max Act: 5.3450. Min Act: -0.1700
Data Index: 3447195 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4387. Min Range: -5.4387
Max Act: 5.3137. Min Act: -0.1700
Data Index: 1082429 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4387. Min Range: -5.4387
Max Act: 5.3450. Min Act: -0.1700
Data Index: 6772589 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4387. Min Range: -5.4387
Max Act: 5.3450. Min Act: -0.1700
Data Index: 6436401 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4387. Min Range: -5.4387
Max Act: 5.3762. Min Act: -0.1700
Data Index: 6417792 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4387. Min Range: -5.4387
Max Act: 5.3137. Min Act: -0.1700
Data Index: 4762721 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4387. Min Range: -5.4387
Max Act: 5.3137. Min Act: -0.1700
Data Index: 1313772 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4387. Min Range: -5.4387
Max Act: 5.2825. Min Act: -0.1700
Data Index: 5642861 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19