Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3448 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3983. Min Range: -4.3983
Max Act: 4.3983. Min Act: -0.1700
Data Index: 3763629 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3983. Min Range: -4.3983
Max Act: 4.2420. Min Act: -0.1700
Data Index: 8088943 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3983. Min Range: -4.3983
Max Act: 4.1482. Min Act: -0.1700
Data Index: 1862676 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3983. Min Range: -4.3983
Max Act: 4.1170. Min Act: -0.1700
Data Index: 534612 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3983. Min Range: -4.3983
Max Act: 4.0545. Min Act: -0.1700
Data Index: 5081732 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3983. Min Range: -4.3983
Max Act: 4.0545. Min Act: -0.1700
Data Index: 8416816 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3983. Min Range: -4.3983
Max Act: 4.0232. Min Act: -0.1700
Data Index: 4135207 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3983. Min Range: -4.3983
Max Act: 3.9607. Min Act: -0.1700
Data Index: 5380087 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3983. Min Range: -4.3983
Max Act: 3.9607. Min Act: -0.1700
Data Index: 6581531 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3983. Min Range: -4.3983
Max Act: 3.9607. Min Act: -0.1700
Data Index: 1673244 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3983. Min Range: -4.3983
Max Act: 3.9607. Min Act: -0.1700
Data Index: 65124 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3983. Min Range: -4.3983
Max Act: 3.9607. Min Act: -0.1700
Data Index: 4955273 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3983. Min Range: -4.3983
Max Act: 3.9607. Min Act: -0.1700
Data Index: 7498186 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3983. Min Range: -4.3983
Max Act: 3.9607. Min Act: -0.1700
Data Index: 7144469 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3983. Min Range: -4.3983
Max Act: 3.9294. Min Act: -0.1700
Data Index: 3323685 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3983. Min Range: -4.3983
Max Act: 3.8981. Min Act: -0.1700
Data Index: 7849193 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3983. Min Range: -4.3983
Max Act: 3.9294. Min Act: -0.1700
Data Index: 8471833 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3983. Min Range: -4.3983
Max Act: 3.9294. Min Act: -0.1700
Data Index: 4135204 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3983. Min Range: -4.3983
Max Act: 3.8981. Min Act: -0.1700
Data Index: 6805123 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3983. Min Range: -4.3983
Max Act: 3.8981. Min Act: -0.1700
Data Index: 2651731 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19