Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5373 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8456. Min Range: -3.8456
Max Act: 3.8456. Min Act: -0.1700
Data Index: 6854433 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8456. Min Range: -3.8456
Max Act: 3.8456. Min Act: -0.1700
Data Index: 7788501 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8456. Min Range: -3.8456
Max Act: 3.8456. Min Act: -0.1700
Data Index: 8689938 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8456. Min Range: -3.8456
Max Act: 3.8456. Min Act: -0.1700
Data Index: 6731417 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8456. Min Range: -3.8456
Max Act: 3.8143. Min Act: -0.1700
Data Index: 855944 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8456. Min Range: -3.8456
Max Act: 3.8143. Min Act: -0.1700
Data Index: 3961106 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8456. Min Range: -3.8456
Max Act: 3.8143. Min Act: -0.1700
Data Index: 1792252 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8456. Min Range: -3.8456
Max Act: 3.7830. Min Act: -0.1700
Data Index: 3961108 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8456. Min Range: -3.8456
Max Act: 3.8143. Min Act: -0.1700
Data Index: 3312435 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8456. Min Range: -3.8456
Max Act: 3.8143. Min Act: -0.1700
Data Index: 3312437 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8456. Min Range: -3.8456
Max Act: 3.8143. Min Act: -0.1700
Data Index: 286306 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8456. Min Range: -3.8456
Max Act: 3.8143. Min Act: -0.1700
Data Index: 286308 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8456. Min Range: -3.8456
Max Act: 3.8143. Min Act: -0.1700
Data Index: 3312433 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8456. Min Range: -3.8456
Max Act: 3.7830. Min Act: -0.1700
Data Index: 3220031 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8456. Min Range: -3.8456
Max Act: 3.8456. Min Act: -0.1700
Data Index: 525329 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8456. Min Range: -3.8456
Max Act: 3.8143. Min Act: -0.1700
Data Index: 2022026 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8456. Min Range: -3.8456
Max Act: 3.8143. Min Act: -0.1700
Data Index: 1684333 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8456. Min Range: -3.8456
Max Act: 3.8143. Min Act: -0.1700
Data Index: 525325 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8456. Min Range: -3.8456
Max Act: 3.8143. Min Act: -0.1700
Data Index: 1684335 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8456. Min Range: -3.8456
Max Act: 3.8143. Min Act: -0.1700
Data Index: 2022024 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19