Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3078 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6901. Min Range: -3.6901
Max Act: 3.6901. Min Act: -0.1700
Data Index: 1985384 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6901. Min Range: -3.6901
Max Act: 3.6901. Min Act: -0.1700
Data Index: 6475001 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6901. Min Range: -3.6901
Max Act: 3.6431. Min Act: -0.1700
Data Index: 1442024 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6901. Min Range: -3.6901
Max Act: 3.6431. Min Act: -0.1700
Data Index: 37640 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6901. Min Range: -3.6901
Max Act: 3.6431. Min Act: -0.1700
Data Index: 7557959 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6901. Min Range: -3.6901
Max Act: 3.6431. Min Act: -0.1700
Data Index: 7721730 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6901. Min Range: -3.6901
Max Act: 3.6431. Min Act: -0.1700
Data Index: 2929442 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6901. Min Range: -3.6901
Max Act: 3.6275. Min Act: -0.1700
Data Index: 7487846 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6901. Min Range: -3.6901
Max Act: 3.6431. Min Act: -0.1700
Data Index: 6959982 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6901. Min Range: -3.6901
Max Act: 3.6431. Min Act: -0.1700
Data Index: 7721727 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6901. Min Range: -3.6901
Max Act: 3.6431. Min Act: -0.1700
Data Index: 7721712 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6901. Min Range: -3.6901
Max Act: 3.6431. Min Act: -0.1700
Data Index: 7721717 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6901. Min Range: -3.6901
Max Act: 3.6431. Min Act: -0.1700
Data Index: 3626970 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6901. Min Range: -3.6901
Max Act: 3.6431. Min Act: -0.1700
Data Index: 7721713 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6901. Min Range: -3.6901
Max Act: 3.6431. Min Act: -0.1700
Data Index: 39672 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6901. Min Range: -3.6901
Max Act: 3.6275. Min Act: -0.1700
Data Index: 3203216 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6901. Min Range: -3.6901
Max Act: 3.6275. Min Act: -0.1700
Data Index: 3362798 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6901. Min Range: -3.6901
Max Act: 3.6275. Min Act: -0.1700
Data Index: 17961 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6901. Min Range: -3.6901
Max Act: 3.6275. Min Act: -0.1700
Data Index: 3503883 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6901. Min Range: -3.6901
Max Act: 3.6275. Min Act: -0.1700
Data Index: 7721683 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19