Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2600 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6082. Min Range: -4.6082
Max Act: 4.6082. Min Act: -0.1700
Data Index: 7520157 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6082. Min Range: -4.6082
Max Act: 4.5145. Min Act: -0.1699
Data Index: 3352790 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6082. Min Range: -4.6082
Max Act: 4.4207. Min Act: -0.1700
Data Index: 575249 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6082. Min Range: -4.6082
Max Act: 4.4207. Min Act: -0.1666
Data Index: 2087144 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6082. Min Range: -4.6082
Max Act: 4.3895. Min Act: -0.1699
Data Index: 5416914 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6082. Min Range: -4.6082
Max Act: 4.3582. Min Act: -0.1700
Data Index: 7520171 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6082. Min Range: -4.6082
Max Act: 4.3270. Min Act: -0.1700
Data Index: 4726515 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6082. Min Range: -4.6082
Max Act: 4.3270. Min Act: -0.1700
Data Index: 5416910 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6082. Min Range: -4.6082
Max Act: 4.2957. Min Act: -0.1700
Data Index: 6758153 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6082. Min Range: -4.6082
Max Act: 4.2645. Min Act: -0.1700
Data Index: 3088048 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6082. Min Range: -4.6082
Max Act: 4.2332. Min Act: -0.1700
Data Index: 7520165 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6082. Min Range: -4.6082
Max Act: 4.2332. Min Act: -0.1700
Data Index: 4172919 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6082. Min Range: -4.6082
Max Act: 4.2332. Min Act: -0.1700
Data Index: 7520160 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6082. Min Range: -4.6082
Max Act: 4.1707. Min Act: -0.1700
Data Index: 7520156 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6082. Min Range: -4.6082
Max Act: 4.1707. Min Act: -0.1700
Data Index: 7520177 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6082. Min Range: -4.6082
Max Act: 4.2020. Min Act: -0.1700
Data Index: 7520154 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6082. Min Range: -4.6082
Max Act: 4.1707. Min Act: -0.1700
Data Index: 5902171 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6082. Min Range: -4.6082
Max Act: 4.1707. Min Act: -0.1700
Data Index: 4853419 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6082. Min Range: -4.6082
Max Act: 4.1395. Min Act: -0.1700
Data Index: 7520159 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6082. Min Range: -4.6082
Max Act: 4.1395. Min Act: -0.1700
Data Index: 6882913 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19