Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6369 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6524. Min Range: -7.6524
Max Act: 7.6524. Min Act: -0.1700
Data Index: 5795200 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6524. Min Range: -7.6524
Max Act: 7.5274. Min Act: -0.1700
Data Index: 6955240 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6524. Min Range: -7.6524
Max Act: 7.5274. Min Act: -0.1700
Data Index: 3929059 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6524. Min Range: -7.6524
Max Act: 7.4024. Min Act: -0.1700
Data Index: 132955 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6524. Min Range: -7.6524
Max Act: 7.3399. Min Act: -0.1700
Data Index: 4956956 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6524. Min Range: -7.6524
Max Act: 7.3399. Min Act: -0.1700
Data Index: 7307552 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6524. Min Range: -7.6524
Max Act: 7.2774. Min Act: -0.1700
Data Index: 2962630 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6524. Min Range: -7.6524
Max Act: 7.2774. Min Act: -0.1700
Data Index: 7963815 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6524. Min Range: -7.6524
Max Act: 7.2462. Min Act: -0.1700
Data Index: 6379246 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6524. Min Range: -7.6524
Max Act: 7.1837. Min Act: -0.1700
Data Index: 8736734 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6524. Min Range: -7.6524
Max Act: 7.1837. Min Act: -0.1700
Data Index: 5105752 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6524. Min Range: -7.6524
Max Act: 7.1524. Min Act: -0.1700
Data Index: 4313415 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6524. Min Range: -7.6524
Max Act: 7.1212. Min Act: -0.1700
Data Index: 8276431 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6524. Min Range: -7.6524
Max Act: 7.0587. Min Act: -0.1700
Data Index: 5701134 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6524. Min Range: -7.6524
Max Act: 7.0587. Min Act: -0.1700
Data Index: 2827322 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6524. Min Range: -7.6524
Max Act: 7.0899. Min Act: -0.1700
Data Index: 8668963 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6524. Min Range: -7.6524
Max Act: 6.9962. Min Act: -0.1700
Data Index: 5533732 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6524. Min Range: -7.6524
Max Act: 6.9962. Min Act: -0.1700
Data Index: 8283591 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6524. Min Range: -7.6524
Max Act: 6.9962. Min Act: -0.1700
Data Index: 426862 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6524. Min Range: -7.6524
Max Act: 6.9962. Min Act: -0.1700
Data Index: 5336046 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19