Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6035 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7977. Min Range: -3.7977
Max Act: 3.7977. Min Act: -0.1700
Data Index: 8324293 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7977. Min Range: -3.7977
Max Act: 3.6570. Min Act: -0.1700
Data Index: 1623458 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7977. Min Range: -3.7977
Max Act: 3.6413. Min Act: -0.1700
Data Index: 8324289 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7977. Min Range: -3.7977
Max Act: 3.6257. Min Act: -0.1700
Data Index: 3091406 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7977. Min Range: -3.7977
Max Act: 3.6100. Min Act: -0.1700
Data Index: 3454793 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7977. Min Range: -3.7977
Max Act: 3.5787. Min Act: -0.1700
Data Index: 6324792 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7977. Min Range: -3.7977
Max Act: 3.5161. Min Act: -0.1700
Data Index: 6813029 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7977. Min Range: -3.7977
Max Act: 3.5004. Min Act: -0.1700
Data Index: 6438857 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7977. Min Range: -3.7977
Max Act: 3.4848. Min Act: -0.1700
Data Index: 771716 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7977. Min Range: -3.7977
Max Act: 3.5004. Min Act: -0.1700
Data Index: 6245988 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7977. Min Range: -3.7977
Max Act: 3.5161. Min Act: -0.1700
Data Index: 4733791 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7977. Min Range: -3.7977
Max Act: 3.4691. Min Act: -0.1700
Data Index: 7801967 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7977. Min Range: -3.7977
Max Act: 3.4377. Min Act: -0.1700
Data Index: 7012990 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7977. Min Range: -3.7977
Max Act: 3.4221. Min Act: -0.1700
Data Index: 6687503 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7977. Min Range: -3.7977
Max Act: 3.4064. Min Act: -0.1700
Data Index: 163815 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7977. Min Range: -3.7977
Max Act: 3.4064. Min Act: -0.1700
Data Index: 4761456 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7977. Min Range: -3.7977
Max Act: 3.4064. Min Act: -0.1700
Data Index: 7018914 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7977. Min Range: -3.7977
Max Act: 3.4064. Min Act: -0.1700
Data Index: 4475743 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7977. Min Range: -3.7977
Max Act: 3.4064. Min Act: -0.1700
Data Index: 4405705 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7977. Min Range: -3.7977
Max Act: 3.3594. Min Act: -0.1700
Data Index: 6180502 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19