Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2283 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2878. Min Range: -3.2878
Max Act: 3.2878. Min Act: -0.1700
Data Index: 7003445 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2878. Min Range: -3.2878
Max Act: 3.2250. Min Act: -0.1700
Data Index: 1500971 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2878. Min Range: -3.2878
Max Act: 3.2407. Min Act: -0.1700
Data Index: 8751554 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2878. Min Range: -3.2878
Max Act: 3.2092. Min Act: -0.1700
Data Index: 5400709 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2878. Min Range: -3.2878
Max Act: 3.2092. Min Act: -0.1700
Data Index: 628274 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2878. Min Range: -3.2878
Max Act: 3.1463. Min Act: -0.1700
Data Index: 1154141 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2878. Min Range: -3.2878
Max Act: 3.1463. Min Act: -0.1700
Data Index: 1048938 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2878. Min Range: -3.2878
Max Act: 3.1148. Min Act: -0.1700
Data Index: 8137443 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2878. Min Range: -3.2878
Max Act: 3.0991. Min Act: -0.1699
Data Index: 8308404 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2878. Min Range: -3.2878
Max Act: 3.1306. Min Act: -0.1700
Data Index: 4014638 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2878. Min Range: -3.2878
Max Act: 3.1148. Min Act: -0.1700
Data Index: 7510732 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2878. Min Range: -3.2878
Max Act: 3.0991. Min Act: -0.1700
Data Index: 950950 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2878. Min Range: -3.2878
Max Act: 3.0833. Min Act: -0.1700
Data Index: 4573385 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2878. Min Range: -3.2878
Max Act: 3.0991. Min Act: -0.1700
Data Index: 4297166 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2878. Min Range: -3.2878
Max Act: 3.0675. Min Act: -0.1700
Data Index: 3241503 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2878. Min Range: -3.2878
Max Act: 3.0675. Min Act: -0.1700
Data Index: 3168304 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2878. Min Range: -3.2878
Max Act: 3.0675. Min Act: -0.1700
Data Index: 6474958 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2878. Min Range: -3.2878
Max Act: 3.0517. Min Act: -0.1700
Data Index: 3507793 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2878. Min Range: -3.2878
Max Act: 3.0517. Min Act: -0.1700
Data Index: 4931981 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2878. Min Range: -3.2878
Max Act: 3.0517. Min Act: -0.1700
Data Index: 673907 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19