Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2681 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4303. Min Range: -6.4303
Max Act: 6.4303. Min Act: -0.1700
Data Index: 1564298 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4303. Min Range: -6.4303
Max Act: 6.2428. Min Act: -0.1700
Data Index: 4690837 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4303. Min Range: -6.4303
Max Act: 6.0553. Min Act: -0.1700
Data Index: 8334173 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4303. Min Range: -6.4303
Max Act: 6.0240. Min Act: -0.1700
Data Index: 4090060 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4303. Min Range: -6.4303
Max Act: 6.0240. Min Act: -0.1700
Data Index: 4609726 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4303. Min Range: -6.4303
Max Act: 6.0240. Min Act: -0.1700
Data Index: 6135470 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4303. Min Range: -6.4303
Max Act: 5.9615. Min Act: -0.1700
Data Index: 602185 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4303. Min Range: -6.4303
Max Act: 5.8990. Min Act: -0.1700
Data Index: 479233 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4303. Min Range: -6.4303
Max Act: 5.8365. Min Act: -0.1700
Data Index: 7499456 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4303. Min Range: -6.4303
Max Act: 5.8053. Min Act: -0.1700
Data Index: 8286629 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4303. Min Range: -6.4303
Max Act: 5.8053. Min Act: -0.1700
Data Index: 4303584 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4303. Min Range: -6.4303
Max Act: 5.7740. Min Act: -0.1700
Data Index: 3745827 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4303. Min Range: -6.4303
Max Act: 5.7428. Min Act: -0.1700
Data Index: 6209 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4303. Min Range: -6.4303
Max Act: 5.7428. Min Act: -0.1700
Data Index: 6129295 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4303. Min Range: -6.4303
Max Act: 5.7115. Min Act: -0.1700
Data Index: 8033381 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4303. Min Range: -6.4303
Max Act: 5.7428. Min Act: -0.1700
Data Index: 1056310 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4303. Min Range: -6.4303
Max Act: 5.7428. Min Act: -0.1700
Data Index: 3021375 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4303. Min Range: -6.4303
Max Act: 5.7115. Min Act: -0.1700
Data Index: 2010278 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4303. Min Range: -6.4303
Max Act: 5.7115. Min Act: -0.1700
Data Index: 4534714 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4303. Min Range: -6.4303
Max Act: 5.6803. Min Act: -0.1700
Data Index: 3068112 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19