Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2442 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5098. Min Range: -2.5098
Max Act: 2.5098. Min Act: -0.1700
Data Index: 69139 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5098. Min Range: -2.5098
Max Act: 2.4449. Min Act: -0.1700
Data Index: 8527408 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5098. Min Range: -2.5098
Max Act: 2.4286. Min Act: -0.1700
Data Index: 237868 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5098. Min Range: -2.5098
Max Act: 2.3797. Min Act: -0.1700
Data Index: 6517702 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5098. Min Range: -2.5098
Max Act: 2.3797. Min Act: -0.1700
Data Index: 4725257 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5098. Min Range: -2.5098
Max Act: 2.3633. Min Act: -0.1700
Data Index: 3455934 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5098. Min Range: -2.5098
Max Act: 2.3797. Min Act: -0.1700
Data Index: 5761054 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5098. Min Range: -2.5098
Max Act: 2.3633. Min Act: -0.1700
Data Index: 8708149 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5098. Min Range: -2.5098
Max Act: 2.3469. Min Act: -0.1700
Data Index: 5549551 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5098. Min Range: -2.5098
Max Act: 2.3469. Min Act: -0.1700
Data Index: 5860898 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5098. Min Range: -2.5098
Max Act: 2.3469. Min Act: -0.1700
Data Index: 4406546 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5098. Min Range: -2.5098
Max Act: 2.3469. Min Act: -0.1700
Data Index: 779261 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5098. Min Range: -2.5098
Max Act: 2.3305. Min Act: -0.1700
Data Index: 543475 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5098. Min Range: -2.5098
Max Act: 2.3141. Min Act: -0.1700
Data Index: 3214040 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5098. Min Range: -2.5098
Max Act: 2.3305. Min Act: -0.1700
Data Index: 7436417 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5098. Min Range: -2.5098
Max Act: 2.3141. Min Act: -0.1700
Data Index: 1946156 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5098. Min Range: -2.5098
Max Act: 2.3141. Min Act: -0.1700
Data Index: 7908832 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5098. Min Range: -2.5098
Max Act: 2.3141. Min Act: -0.1700
Data Index: 1833661 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5098. Min Range: -2.5098
Max Act: 2.2977. Min Act: -0.1700
Data Index: 3532725 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5098. Min Range: -2.5098
Max Act: 2.2812. Min Act: -0.1700
Data Index: 6560063 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #19