Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3083 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7156. Min Range: -9.7156
Max Act: 9.7156. Min Act: -0.1700
Data Index: 3706530 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7156. Min Range: -9.7156
Max Act: 9.5281. Min Act: -0.1700
Data Index: 4326518 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7156. Min Range: -9.7156
Max Act: 9.5281. Min Act: -0.1700
Data Index: 3185170 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7156. Min Range: -9.7156
Max Act: 9.4656. Min Act: -0.1700
Data Index: 3274035 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7156. Min Range: -9.7156
Max Act: 9.5281. Min Act: -0.1700
Data Index: 1405453 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7156. Min Range: -9.7156
Max Act: 9.4656. Min Act: -0.1700
Data Index: 3932186 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7156. Min Range: -9.7156
Max Act: 9.4031. Min Act: -0.1700
Data Index: 568769 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7156. Min Range: -9.7156
Max Act: 9.3406. Min Act: -0.1700
Data Index: 8747273 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7156. Min Range: -9.7156
Max Act: 9.3406. Min Act: -0.1700
Data Index: 7770702 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7156. Min Range: -9.7156
Max Act: 9.3406. Min Act: -0.1700
Data Index: 6030829 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7156. Min Range: -9.7156
Max Act: 9.3406. Min Act: -0.1700
Data Index: 5297295 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7156. Min Range: -9.7156
Max Act: 9.2781. Min Act: -0.1700
Data Index: 8805075 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7156. Min Range: -9.7156
Max Act: 9.2781. Min Act: -0.1700
Data Index: 6675006 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7156. Min Range: -9.7156
Max Act: 9.2781. Min Act: -0.1700
Data Index: 8271940 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7156. Min Range: -9.7156
Max Act: 9.2156. Min Act: -0.1700
Data Index: 7270811 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7156. Min Range: -9.7156
Max Act: 9.2156. Min Act: -0.1700
Data Index: 8193773 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7156. Min Range: -9.7156
Max Act: 9.1531. Min Act: -0.1700
Data Index: 8822601 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7156. Min Range: -9.7156
Max Act: 9.0906. Min Act: -0.1700
Data Index: 3784595 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7156. Min Range: -9.7156
Max Act: 9.1531. Min Act: -0.1700
Data Index: 7458883 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7156. Min Range: -9.7156
Max Act: 9.1531. Min Act: -0.1700
Data Index: 5295681 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #19