Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6077 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.7314. Min Act: -0.1700
Data Index: 7474251 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.7314. Min Act: -0.1700
Data Index: 554775 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.7001. Min Act: -0.1700
Data Index: 5518383 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.7001. Min Act: -0.1700
Data Index: 5673649 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.7001. Min Act: -0.1700
Data Index: 1754094 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.6689. Min Act: -0.1700
Data Index: 2704029 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.6689. Min Act: -0.1700
Data Index: 3270886 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.6376. Min Act: -0.1700
Data Index: 4276160 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.6376. Min Act: -0.1700
Data Index: 185540 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.6376. Min Act: -0.1700
Data Index: 2840489 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.6376. Min Act: -0.1700
Data Index: 5020069 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.6064. Min Act: -0.1700
Data Index: 3666413 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.6376. Min Act: -0.1700
Data Index: 3800579 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.6064. Min Act: -0.1700
Data Index: 5530514 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.5751. Min Act: -0.1700
Data Index: 7199020 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.5751. Min Act: -0.1700
Data Index: 345806 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.5751. Min Act: -0.1700
Data Index: 1325563 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.5751. Min Act: -0.1700
Data Index: 3900538 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.5751. Min Act: -0.1700
Data Index: 4090359 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7314. Min Range: -5.7314
Max Act: 5.5439. Min Act: -0.1700
Data Index: 1742510 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19