Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5983 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8195. Min Range: -6.8195
Max Act: 6.8195. Min Act: -0.1700
Data Index: 6307208 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8195. Min Range: -6.8195
Max Act: 6.4758. Min Act: -0.1700
Data Index: 4768518 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8195. Min Range: -6.8195
Max Act: 6.3820. Min Act: -0.1700
Data Index: 4444160 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8195. Min Range: -6.8195
Max Act: 6.2258. Min Act: -0.1700
Data Index: 6073752 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8195. Min Range: -6.8195
Max Act: 6.1945. Min Act: -0.1700
Data Index: 3765975 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8195. Min Range: -6.8195
Max Act: 6.1945. Min Act: -0.1700
Data Index: 2067892 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8195. Min Range: -6.8195
Max Act: 6.1633. Min Act: -0.1700
Data Index: 916411 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8195. Min Range: -6.8195
Max Act: 6.1320. Min Act: -0.1700
Data Index: 366477 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8195. Min Range: -6.8195
Max Act: 6.1320. Min Act: -0.1700
Data Index: 873570 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8195. Min Range: -6.8195
Max Act: 6.1008. Min Act: -0.1700
Data Index: 4576400 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8195. Min Range: -6.8195
Max Act: 6.1008. Min Act: -0.1700
Data Index: 4023349 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8195. Min Range: -6.8195
Max Act: 6.0695. Min Act: -0.1700
Data Index: 5166418 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8195. Min Range: -6.8195
Max Act: 6.1008. Min Act: -0.1700
Data Index: 3660106 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8195. Min Range: -6.8195
Max Act: 6.1008. Min Act: -0.1700
Data Index: 5404975 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8195. Min Range: -6.8195
Max Act: 6.1008. Min Act: -0.1700
Data Index: 7575700 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8195. Min Range: -6.8195
Max Act: 6.0695. Min Act: -0.1700
Data Index: 315702 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8195. Min Range: -6.8195
Max Act: 6.0383. Min Act: -0.1700
Data Index: 6330583 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8195. Min Range: -6.8195
Max Act: 6.0070. Min Act: -0.1700
Data Index: 316641 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8195. Min Range: -6.8195
Max Act: 6.0383. Min Act: -0.1700
Data Index: 6689214 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8195. Min Range: -6.8195
Max Act: 6.0070. Min Act: -0.1700
Data Index: 3187957 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19