Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 717 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7670. Min Range: -4.7670
Max Act: 4.7670. Min Act: -0.1700
Data Index: 2632726 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7670. Min Range: -4.7670
Max Act: 4.7358. Min Act: -0.1700
Data Index: 7267570 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7670. Min Range: -4.7670
Max Act: 4.6733. Min Act: -0.1700
Data Index: 3312025 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7670. Min Range: -4.7670
Max Act: 4.6420. Min Act: -0.1700
Data Index: 5926742 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7670. Min Range: -4.7670
Max Act: 4.6733. Min Act: -0.1700
Data Index: 4362347 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7670. Min Range: -4.7670
Max Act: 4.6108. Min Act: -0.1700
Data Index: 3295453 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7670. Min Range: -4.7670
Max Act: 4.5795. Min Act: -0.1700
Data Index: 466595 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7670. Min Range: -4.7670
Max Act: 4.5483. Min Act: -0.1700
Data Index: 6979142 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7670. Min Range: -4.7670
Max Act: 4.5483. Min Act: -0.1700
Data Index: 2547028 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7670. Min Range: -4.7670
Max Act: 4.4858. Min Act: -0.1700
Data Index: 6520231 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7670. Min Range: -4.7670
Max Act: 4.5483. Min Act: -0.1700
Data Index: 1701471 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7670. Min Range: -4.7670
Max Act: 4.5170. Min Act: -0.1700
Data Index: 4429486 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7670. Min Range: -4.7670
Max Act: 4.4858. Min Act: -0.1700
Data Index: 4934193 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7670. Min Range: -4.7670
Max Act: 4.5170. Min Act: -0.1700
Data Index: 2808840 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7670. Min Range: -4.7670
Max Act: 4.4545. Min Act: -0.1700
Data Index: 6074642 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7670. Min Range: -4.7670
Max Act: 4.4545. Min Act: -0.1700
Data Index: 3460909 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7670. Min Range: -4.7670
Max Act: 4.4233. Min Act: -0.1700
Data Index: 7190155 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7670. Min Range: -4.7670
Max Act: 4.4233. Min Act: -0.1700
Data Index: 5273052 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7670. Min Range: -4.7670
Max Act: 4.4233. Min Act: -0.1700
Data Index: 919995 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7670. Min Range: -4.7670
Max Act: 4.4233. Min Act: -0.1700
Data Index: 1931399 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #19