Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2808 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8386. Min Range: -7.8386
Max Act: 7.8386. Min Act: -0.1700
Data Index: 2923430 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8386. Min Range: -7.8386
Max Act: 7.7761. Min Act: -0.1700
Data Index: 2827437 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8386. Min Range: -7.8386
Max Act: 7.7136. Min Act: -0.1700
Data Index: 4365999 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8386. Min Range: -7.8386
Max Act: 7.6824. Min Act: -0.1700
Data Index: 3011515 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8386. Min Range: -7.8386
Max Act: 7.6199. Min Act: -0.1700
Data Index: 6064625 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8386. Min Range: -7.8386
Max Act: 7.5886. Min Act: -0.1700
Data Index: 5218765 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8386. Min Range: -7.8386
Max Act: 7.5574. Min Act: -0.1700
Data Index: 4634781 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8386. Min Range: -7.8386
Max Act: 7.5886. Min Act: -0.1700
Data Index: 373720 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8386. Min Range: -7.8386
Max Act: 7.5574. Min Act: -0.1700
Data Index: 350627 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8386. Min Range: -7.8386
Max Act: 7.5261. Min Act: -0.1700
Data Index: 6698589 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8386. Min Range: -7.8386
Max Act: 7.5261. Min Act: -0.1700
Data Index: 1200374 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8386. Min Range: -7.8386
Max Act: 7.4949. Min Act: -0.1700
Data Index: 4987668 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8386. Min Range: -7.8386
Max Act: 7.4949. Min Act: -0.1700
Data Index: 1239161 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8386. Min Range: -7.8386
Max Act: 7.4949. Min Act: -0.1700
Data Index: 5353232 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8386. Min Range: -7.8386
Max Act: 7.4636. Min Act: -0.1700
Data Index: 5792302 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8386. Min Range: -7.8386
Max Act: 7.4636. Min Act: -0.1700
Data Index: 329232 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8386. Min Range: -7.8386
Max Act: 7.4636. Min Act: -0.1700
Data Index: 1673754 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8386. Min Range: -7.8386
Max Act: 7.4324. Min Act: -0.1700
Data Index: 3759888 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8386. Min Range: -7.8386
Max Act: 7.3699. Min Act: -0.1700
Data Index: 5723136 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8386. Min Range: -7.8386
Max Act: 7.4011. Min Act: -0.1700
Data Index: 5250274 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19