Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1396 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0977. Min Range: -5.0977
Max Act: 5.0977. Min Act: -0.1700
Data Index: 306407 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0977. Min Range: -5.0977
Max Act: 4.5351. Min Act: -0.1700
Data Index: 855074 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0977. Min Range: -5.0977
Max Act: 4.5039. Min Act: -0.1700
Data Index: 7623717 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0977. Min Range: -5.0977
Max Act: 4.5039. Min Act: -0.1700
Data Index: 1834240 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0977. Min Range: -5.0977
Max Act: 4.4726. Min Act: -0.1700
Data Index: 3088922 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0977. Min Range: -5.0977
Max Act: 4.4726. Min Act: -0.1700
Data Index: 748973 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0977. Min Range: -5.0977
Max Act: 4.4726. Min Act: -0.1700
Data Index: 4003532 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0977. Min Range: -5.0977
Max Act: 4.4414. Min Act: -0.1700
Data Index: 573243 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0977. Min Range: -5.0977
Max Act: 4.4101. Min Act: -0.1700
Data Index: 3047793 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0977. Min Range: -5.0977
Max Act: 4.4101. Min Act: -0.1700
Data Index: 5265471 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0977. Min Range: -5.0977
Max Act: 4.4101. Min Act: -0.1700
Data Index: 6557551 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0977. Min Range: -5.0977
Max Act: 4.3476. Min Act: -0.1700
Data Index: 374788 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0977. Min Range: -5.0977
Max Act: 4.3476. Min Act: -0.1700
Data Index: 5864202 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0977. Min Range: -5.0977
Max Act: 4.3476. Min Act: -0.1700
Data Index: 5665753 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0977. Min Range: -5.0977
Max Act: 4.3476. Min Act: -0.1700
Data Index: 6578963 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0977. Min Range: -5.0977
Max Act: 4.3476. Min Act: -0.1700
Data Index: 6984051 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0977. Min Range: -5.0977
Max Act: 4.3164. Min Act: -0.1700
Data Index: 2800332 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0977. Min Range: -5.0977
Max Act: 4.3164. Min Act: -0.1700
Data Index: 3764869 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0977. Min Range: -5.0977
Max Act: 4.3164. Min Act: -0.1700
Data Index: 923151 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0977. Min Range: -5.0977
Max Act: 4.3164. Min Act: -0.1700
Data Index: 6864708 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19