Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4024 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8695. Min Range: -1.8695
Max Act: 1.8695. Min Act: -0.1697
Data Index: 2903824 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8695. Min Range: -1.8695
Max Act: 1.8524. Min Act: -0.1700
Data Index: 2727010 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8695. Min Range: -1.8695
Max Act: 1.8353. Min Act: -0.1700
Data Index: 1049287 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8695. Min Range: -1.8695
Max Act: 1.8181. Min Act: -0.1700
Data Index: 4264402 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8695. Min Range: -1.8695
Max Act: 1.8353. Min Act: -0.1688
Data Index: 6824717 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8695. Min Range: -1.8695
Max Act: 1.8009. Min Act: -0.1700
Data Index: 3058158 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8695. Min Range: -1.8695
Max Act: 1.8181. Min Act: -0.1700
Data Index: 7102093 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8695. Min Range: -1.8695
Max Act: 1.8181. Min Act: -0.1699
Data Index: 3185801 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8695. Min Range: -1.8695
Max Act: 1.8009. Min Act: -0.1700
Data Index: 1542584 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8695. Min Range: -1.8695
Max Act: 1.8009. Min Act: -0.1700
Data Index: 6012125 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8695. Min Range: -1.8695
Max Act: 1.8009. Min Act: -0.1700
Data Index: 2717080 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8695. Min Range: -1.8695
Max Act: 1.8009. Min Act: -0.1700
Data Index: 7366335 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8695. Min Range: -1.8695
Max Act: 1.8009. Min Act: -0.1699
Data Index: 2543032 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8695. Min Range: -1.8695
Max Act: 1.8009. Min Act: -0.1700
Data Index: 5331851 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8695. Min Range: -1.8695
Max Act: 1.8009. Min Act: -0.1698
Data Index: 157080 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8695. Min Range: -1.8695
Max Act: 1.7923. Min Act: -0.1700
Data Index: 7836205 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8695. Min Range: -1.8695
Max Act: 1.7837. Min Act: -0.1700
Data Index: 7881510 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8695. Min Range: -1.8695
Max Act: 1.7837. Min Act: -0.1700
Data Index: 4619211 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8695. Min Range: -1.8695
Max Act: 1.7837. Min Act: -0.1699
Data Index: 6728635 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8695. Min Range: -1.8695
Max Act: 1.7751. Min Act: -0.1700
Data Index: 6083349 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19