Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4954 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8161. Min Range: -6.8161
Max Act: 6.8161. Min Act: -0.1700
Data Index: 3128365 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8161. Min Range: -6.8161
Max Act: 6.8161. Min Act: -0.1700
Data Index: 667565 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8161. Min Range: -6.8161
Max Act: 6.6911. Min Act: -0.1700
Data Index: 5151066 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8161. Min Range: -6.8161
Max Act: 6.5973. Min Act: -0.1700
Data Index: 6878785 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8161. Min Range: -6.8161
Max Act: 6.5661. Min Act: -0.1700
Data Index: 449788 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8161. Min Range: -6.8161
Max Act: 6.5348. Min Act: -0.1700
Data Index: 3584665 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8161. Min Range: -6.8161
Max Act: 6.4723. Min Act: -0.1700
Data Index: 3599829 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8161. Min Range: -6.8161
Max Act: 6.4723. Min Act: -0.1700
Data Index: 762820 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8161. Min Range: -6.8161
Max Act: 6.3473. Min Act: -0.1700
Data Index: 8709587 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8161. Min Range: -6.8161
Max Act: 6.3473. Min Act: -0.1700
Data Index: 4447211 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8161. Min Range: -6.8161
Max Act: 6.3473. Min Act: -0.1700
Data Index: 6731100 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8161. Min Range: -6.8161
Max Act: 6.2848. Min Act: -0.1700
Data Index: 1213834 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8161. Min Range: -6.8161
Max Act: 6.2848. Min Act: -0.1700
Data Index: 5741359 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8161. Min Range: -6.8161
Max Act: 6.2536. Min Act: -0.1700
Data Index: 2715277 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8161. Min Range: -6.8161
Max Act: 6.2223. Min Act: -0.1700
Data Index: 4625478 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8161. Min Range: -6.8161
Max Act: 6.2223. Min Act: -0.1700
Data Index: 3572928 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8161. Min Range: -6.8161
Max Act: 6.1911. Min Act: -0.1700
Data Index: 6486919 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8161. Min Range: -6.8161
Max Act: 6.1286. Min Act: -0.1700
Data Index: 54477 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8161. Min Range: -6.8161
Max Act: 6.1598. Min Act: -0.1700
Data Index: 2803275 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8161. Min Range: -6.8161
Max Act: 6.1286. Min Act: -0.1700
Data Index: 3751987 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19