Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1611 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4971. Min Range: -1.4971
Max Act: 1.4971. Min Act: -0.1700
Data Index: 1301199 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4971. Min Range: -1.4971
Max Act: 1.4444. Min Act: -0.1700
Data Index: 3641167 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4971. Min Range: -1.4971
Max Act: 1.4444. Min Act: -0.1700
Data Index: 3447313 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4971. Min Range: -1.4971
Max Act: 1.4268. Min Act: -0.1700
Data Index: 2429563 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4971. Min Range: -1.4971
Max Act: 1.4532. Min Act: -0.1682
Data Index: 3559251 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4971. Min Range: -1.4971
Max Act: 1.4268. Min Act: -0.1700
Data Index: 6468105 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4971. Min Range: -1.4971
Max Act: 1.4180. Min Act: -0.1689
Data Index: 7975594 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4971. Min Range: -1.4971
Max Act: 1.4180. Min Act: -0.1700
Data Index: 7176260 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4971. Min Range: -1.4971
Max Act: 1.4180. Min Act: -0.1700
Data Index: 7288663 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4971. Min Range: -1.4971
Max Act: 1.4092. Min Act: -0.1700
Data Index: 5516327 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4971. Min Range: -1.4971
Max Act: 1.4004. Min Act: -0.1700
Data Index: 3394372 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4971. Min Range: -1.4971
Max Act: 1.4092. Min Act: -0.1700
Data Index: 103735 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4971. Min Range: -1.4971
Max Act: 1.4004. Min Act: -0.1700
Data Index: 7118044 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4971. Min Range: -1.4971
Max Act: 1.3916. Min Act: -0.1700
Data Index: 5599645 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4971. Min Range: -1.4971
Max Act: 1.3828. Min Act: -0.1700
Data Index: 8679129 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4971. Min Range: -1.4971
Max Act: 1.3916. Min Act: -0.1700
Data Index: 7087435 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4971. Min Range: -1.4971
Max Act: 1.3828. Min Act: -0.1700
Data Index: 4889904 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4971. Min Range: -1.4971
Max Act: 1.3739. Min Act: -0.1700
Data Index: 3580210 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4971. Min Range: -1.4971
Max Act: 1.3828. Min Act: -0.1700
Data Index: 3486222 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4971. Min Range: -1.4971
Max Act: 1.3651. Min Act: -0.1695
Data Index: 5012535 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19