Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3002 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0956. Min Range: -6.0956
Max Act: 6.0956. Min Act: -0.1700
Data Index: 3347605 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0956. Min Range: -6.0956
Max Act: 6.0331. Min Act: -0.1700
Data Index: 7351086 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0956. Min Range: -6.0956
Max Act: 6.0018. Min Act: -0.1700
Data Index: 384386 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0956. Min Range: -6.0956
Max Act: 6.0018. Min Act: -0.1700
Data Index: 698928 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0956. Min Range: -6.0956
Max Act: 5.9393. Min Act: -0.1700
Data Index: 3598975 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0956. Min Range: -6.0956
Max Act: 5.8768. Min Act: -0.1700
Data Index: 4513842 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0956. Min Range: -6.0956
Max Act: 5.8768. Min Act: -0.1700
Data Index: 2526993 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0956. Min Range: -6.0956
Max Act: 5.8456. Min Act: -0.1700
Data Index: 4472857 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0956. Min Range: -6.0956
Max Act: 5.7206. Min Act: -0.1700
Data Index: 2656605 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0956. Min Range: -6.0956
Max Act: 5.7206. Min Act: -0.1700
Data Index: 4156450 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0956. Min Range: -6.0956
Max Act: 5.7206. Min Act: -0.1700
Data Index: 8484203 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0956. Min Range: -6.0956
Max Act: 5.5956. Min Act: -0.1700
Data Index: 691840 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0956. Min Range: -6.0956
Max Act: 5.6268. Min Act: -0.1700
Data Index: 6675855 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0956. Min Range: -6.0956
Max Act: 5.5956. Min Act: -0.1700
Data Index: 7989232 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0956. Min Range: -6.0956
Max Act: 5.5643. Min Act: -0.1700
Data Index: 2836387 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0956. Min Range: -6.0956
Max Act: 5.5643. Min Act: -0.1700
Data Index: 4932006 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0956. Min Range: -6.0956
Max Act: 5.5643. Min Act: -0.1700
Data Index: 4111740 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0956. Min Range: -6.0956
Max Act: 5.5643. Min Act: -0.1700
Data Index: 1506040 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0956. Min Range: -6.0956
Max Act: 5.5018. Min Act: -0.1700
Data Index: 6300453 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0956. Min Range: -6.0956
Max Act: 5.5018. Min Act: -0.1700
Data Index: 7768802 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19