Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1248 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4373. Min Range: -8.4373
Max Act: 8.4373. Min Act: -0.1700
Data Index: 5985462 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4373. Min Range: -8.4373
Max Act: 8.0623. Min Act: -0.1700
Data Index: 53406 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4373. Min Range: -8.4373
Max Act: 8.0623. Min Act: -0.1700
Data Index: 8753950 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4373. Min Range: -8.4373
Max Act: 7.9998. Min Act: -0.1700
Data Index: 1417081 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4373. Min Range: -8.4373
Max Act: 7.9998. Min Act: -0.1700
Data Index: 4164763 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4373. Min Range: -8.4373
Max Act: 7.9998. Min Act: -0.1700
Data Index: 6802403 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4373. Min Range: -8.4373
Max Act: 7.9998. Min Act: -0.1700
Data Index: 2737665 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4373. Min Range: -8.4373
Max Act: 7.9373. Min Act: -0.1700
Data Index: 7261271 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4373. Min Range: -8.4373
Max Act: 7.9373. Min Act: -0.1700
Data Index: 6696336 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4373. Min Range: -8.4373
Max Act: 7.8123. Min Act: -0.1700
Data Index: 6450781 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4373. Min Range: -8.4373
Max Act: 7.8123. Min Act: -0.1700
Data Index: 5513899 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4373. Min Range: -8.4373
Max Act: 7.8123. Min Act: -0.1700
Data Index: 5301601 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4373. Min Range: -8.4373
Max Act: 7.8123. Min Act: -0.1700
Data Index: 787463 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4373. Min Range: -8.4373
Max Act: 7.7498. Min Act: -0.1700
Data Index: 7163757 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4373. Min Range: -8.4373
Max Act: 7.8123. Min Act: -0.1700
Data Index: 7607402 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4373. Min Range: -8.4373
Max Act: 7.7498. Min Act: -0.1700
Data Index: 3919953 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4373. Min Range: -8.4373
Max Act: 7.7498. Min Act: -0.1700
Data Index: 4089615 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4373. Min Range: -8.4373
Max Act: 7.7498. Min Act: -0.1700
Data Index: 1053759 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4373. Min Range: -8.4373
Max Act: 7.6873. Min Act: -0.1700
Data Index: 2222991 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4373. Min Range: -8.4373
Max Act: 7.6873. Min Act: -0.1700
Data Index: 3811291 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19