Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 585 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8107. Min Range: -7.8107
Max Act: 7.8107. Min Act: -0.1700
Data Index: 4625614 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8107. Min Range: -7.8107
Max Act: 7.1857. Min Act: -0.1700
Data Index: 1544618 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8107. Min Range: -7.8107
Max Act: 6.9357. Min Act: -0.1700
Data Index: 4126229 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8107. Min Range: -7.8107
Max Act: 6.9357. Min Act: -0.1700
Data Index: 720101 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8107. Min Range: -7.8107
Max Act: 6.8732. Min Act: -0.1700
Data Index: 2075068 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8107. Min Range: -7.8107
Max Act: 6.8107. Min Act: -0.1700
Data Index: 3373086 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8107. Min Range: -7.8107
Max Act: 6.7794. Min Act: -0.1700
Data Index: 979797 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8107. Min Range: -7.8107
Max Act: 6.6857. Min Act: -0.1700
Data Index: 8628994 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8107. Min Range: -7.8107
Max Act: 6.6544. Min Act: -0.1700
Data Index: 1491590 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8107. Min Range: -7.8107
Max Act: 6.6544. Min Act: -0.1700
Data Index: 6088313 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8107. Min Range: -7.8107
Max Act: 6.6232. Min Act: -0.1700
Data Index: 4288809 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8107. Min Range: -7.8107
Max Act: 6.6544. Min Act: -0.1700
Data Index: 3246102 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8107. Min Range: -7.8107
Max Act: 6.6232. Min Act: -0.1700
Data Index: 6469680 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8107. Min Range: -7.8107
Max Act: 6.6232. Min Act: -0.1700
Data Index: 4962854 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8107. Min Range: -7.8107
Max Act: 6.5294. Min Act: -0.1700
Data Index: 2132764 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8107. Min Range: -7.8107
Max Act: 6.5607. Min Act: -0.1700
Data Index: 8128482 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8107. Min Range: -7.8107
Max Act: 6.5294. Min Act: -0.1700
Data Index: 5431261 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8107. Min Range: -7.8107
Max Act: 6.5607. Min Act: -0.1700
Data Index: 2559381 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8107. Min Range: -7.8107
Max Act: 6.5294. Min Act: -0.1700
Data Index: 293525 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8107. Min Range: -7.8107
Max Act: 6.5294. Min Act: -0.1700
Data Index: 1246885 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19