Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4300 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4018. Min Range: -6.4018
Max Act: 6.4018. Min Act: -0.1700
Data Index: 7935633 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4018. Min Range: -6.4018
Max Act: 5.9018. Min Act: -0.1700
Data Index: 8325206 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4018. Min Range: -6.4018
Max Act: 5.6518. Min Act: -0.1700
Data Index: 4215999 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4018. Min Range: -6.4018
Max Act: 5.6206. Min Act: -0.1700
Data Index: 4288521 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4018. Min Range: -6.4018
Max Act: 5.6206. Min Act: -0.1700
Data Index: 7221168 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4018. Min Range: -6.4018
Max Act: 5.5893. Min Act: -0.1700
Data Index: 1090075 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4018. Min Range: -6.4018
Max Act: 5.6206. Min Act: -0.1700
Data Index: 1181665 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4018. Min Range: -6.4018
Max Act: 5.5581. Min Act: -0.1700
Data Index: 5130045 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4018. Min Range: -6.4018
Max Act: 5.5581. Min Act: -0.1700
Data Index: 6674952 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4018. Min Range: -6.4018
Max Act: 5.5268. Min Act: -0.1700
Data Index: 3225719 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4018. Min Range: -6.4018
Max Act: 5.4956. Min Act: -0.1700
Data Index: 6242641 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4018. Min Range: -6.4018
Max Act: 5.5268. Min Act: -0.1700
Data Index: 2108746 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4018. Min Range: -6.4018
Max Act: 5.4956. Min Act: -0.1700
Data Index: 1889463 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4018. Min Range: -6.4018
Max Act: 5.5268. Min Act: -0.1700
Data Index: 264472 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4018. Min Range: -6.4018
Max Act: 5.4956. Min Act: -0.1700
Data Index: 2675394 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4018. Min Range: -6.4018
Max Act: 5.4956. Min Act: -0.1700
Data Index: 7106764 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4018. Min Range: -6.4018
Max Act: 5.4956. Min Act: -0.1700
Data Index: 6193165 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4018. Min Range: -6.4018
Max Act: 5.4956. Min Act: -0.1700
Data Index: 6952803 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4018. Min Range: -6.4018
Max Act: 5.4643. Min Act: -0.1700
Data Index: 2108727 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4018. Min Range: -6.4018
Max Act: 5.4643. Min Act: -0.1700
Data Index: 6573244 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19