Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1124 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.3953. Min Range: -1.3953
Max Act: 1.3953. Min Act: -0.1695
Data Index: 5789294 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3953. Min Range: -1.3953
Max Act: 1.3865. Min Act: -0.1700
Data Index: 1772073 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3953. Min Range: -1.3953
Max Act: 1.3777. Min Act: -0.1696
Data Index: 2734635 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3953. Min Range: -1.3953
Max Act: 1.3777. Min Act: -0.1691
Data Index: 4564580 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3953. Min Range: -1.3953
Max Act: 1.3689. Min Act: -0.1696
Data Index: 763517 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3953. Min Range: -1.3953
Max Act: 1.3600. Min Act: -0.1698
Data Index: 528675 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3953. Min Range: -1.3953
Max Act: 1.3600. Min Act: -0.1691
Data Index: 6293858 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3953. Min Range: -1.3953
Max Act: 1.3512. Min Act: -0.1677
Data Index: 1715877 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3953. Min Range: -1.3953
Max Act: 1.3512. Min Act: -0.1628
Data Index: 6184932 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3953. Min Range: -1.3953
Max Act: 1.3512. Min Act: -0.1644
Data Index: 8301825 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3953. Min Range: -1.3953
Max Act: 1.3512. Min Act: -0.1621
Data Index: 6294 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3953. Min Range: -1.3953
Max Act: 1.3424. Min Act: -0.1679
Data Index: 521593 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3953. Min Range: -1.3953
Max Act: 1.3336. Min Act: -0.1700
Data Index: 7207928 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3953. Min Range: -1.3953
Max Act: 1.3336. Min Act: -0.1683
Data Index: 1241199 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3953. Min Range: -1.3953
Max Act: 1.3336. Min Act: -0.1699
Data Index: 2807489 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3953. Min Range: -1.3953
Max Act: 1.3248. Min Act: -0.1700
Data Index: 5723106 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3953. Min Range: -1.3953
Max Act: 1.3248. Min Act: -0.1681
Data Index: 7357976 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3953. Min Range: -1.3953
Max Act: 1.3248. Min Act: -0.1670
Data Index: 3955351 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3953. Min Range: -1.3953
Max Act: 1.3160. Min Act: -0.1700
Data Index: 3808669 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3953. Min Range: -1.3953
Max Act: 1.3160. Min Act: -0.1694
Data Index: 5323045 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19