Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 357 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.5472. Min Act: -0.1700
Data Index: 4667441 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.3910. Min Act: -0.1700
Data Index: 1510043 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.2035. Min Act: -0.1700
Data Index: 5150944 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.2035. Min Act: -0.1700
Data Index: 2563347 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.2035. Min Act: -0.1700
Data Index: 287395 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.2035. Min Act: -0.1700
Data Index: 5568685 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.1722. Min Act: -0.1700
Data Index: 4524209 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.1410. Min Act: -0.1700
Data Index: 8215759 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.0785. Min Act: -0.1700
Data Index: 7858836 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.0472. Min Act: -0.1700
Data Index: 1270666 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.0785. Min Act: -0.1700
Data Index: 5903799 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.0472. Min Act: -0.1700
Data Index: 287396 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.0472. Min Act: -0.1700
Data Index: 8241002 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.0472. Min Act: -0.1700
Data Index: 6654251 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.0472. Min Act: -0.1700
Data Index: 2486553 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.0472. Min Act: -0.1700
Data Index: 3380257 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.0159. Min Act: -0.1700
Data Index: 5652914 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.0159. Min Act: -0.1700
Data Index: 308392 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.0159. Min Act: -0.1700
Data Index: 3945986 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5472. Min Range: -4.5472
Max Act: 4.0159. Min Act: -0.1700
Data Index: 4698189 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19