Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2587 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4179. Min Range: -3.4179
Max Act: 3.4179. Min Act: -0.1700
Data Index: 8808820 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4179. Min Range: -3.4179
Max Act: 3.3552. Min Act: -0.1700
Data Index: 4917688 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4179. Min Range: -3.4179
Max Act: 3.3552. Min Act: -0.1700
Data Index: 696285 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4179. Min Range: -3.4179
Max Act: 3.2767. Min Act: -0.1700
Data Index: 4275211 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4179. Min Range: -3.4179
Max Act: 3.2453. Min Act: -0.1700
Data Index: 205649 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4179. Min Range: -3.4179
Max Act: 3.2296. Min Act: -0.1700
Data Index: 7127660 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4179. Min Range: -3.4179
Max Act: 3.2453. Min Act: -0.1700
Data Index: 7870390 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4179. Min Range: -3.4179
Max Act: 3.2296. Min Act: -0.1700
Data Index: 1546620 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4179. Min Range: -3.4179
Max Act: 3.2296. Min Act: -0.1700
Data Index: 5110922 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4179. Min Range: -3.4179
Max Act: 3.2139. Min Act: -0.1700
Data Index: 1825216 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4179. Min Range: -3.4179
Max Act: 3.1982. Min Act: -0.1700
Data Index: 1906108 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4179. Min Range: -3.4179
Max Act: 3.1982. Min Act: -0.1700
Data Index: 6973175 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4179. Min Range: -3.4179
Max Act: 3.1824. Min Act: -0.1700
Data Index: 2898026 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4179. Min Range: -3.4179
Max Act: 3.1824. Min Act: -0.1700
Data Index: 5051323 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4179. Min Range: -3.4179
Max Act: 3.1667. Min Act: -0.1700
Data Index: 7538678 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4179. Min Range: -3.4179
Max Act: 3.1824. Min Act: -0.1700
Data Index: 7441923 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4179. Min Range: -3.4179
Max Act: 3.1824. Min Act: -0.1700
Data Index: 7284544 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4179. Min Range: -3.4179
Max Act: 3.1667. Min Act: -0.1700
Data Index: 6065128 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4179. Min Range: -3.4179
Max Act: 3.1824. Min Act: -0.1700
Data Index: 2053425 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4179. Min Range: -3.4179
Max Act: 3.1510. Min Act: -0.1700
Data Index: 8126535 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19