Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5795 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7278. Min Range: -6.7278
Max Act: 6.7278. Min Act: -0.1700
Data Index: 2383807 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7278. Min Range: -6.7278
Max Act: 6.4778. Min Act: -0.1700
Data Index: 5202890 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7278. Min Range: -6.7278
Max Act: 6.3528. Min Act: -0.1700
Data Index: 4165162 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7278. Min Range: -6.7278
Max Act: 6.3528. Min Act: -0.1700
Data Index: 2586784 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7278. Min Range: -6.7278
Max Act: 6.2278. Min Act: -0.1700
Data Index: 641432 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7278. Min Range: -6.7278
Max Act: 6.1653. Min Act: -0.1700
Data Index: 8824645 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7278. Min Range: -6.7278
Max Act: 6.1653. Min Act: -0.1700
Data Index: 3800427 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7278. Min Range: -6.7278
Max Act: 6.1028. Min Act: -0.1700
Data Index: 5094235 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7278. Min Range: -6.7278
Max Act: 6.1028. Min Act: -0.1700
Data Index: 2042660 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7278. Min Range: -6.7278
Max Act: 6.0716. Min Act: -0.1700
Data Index: 8623300 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7278. Min Range: -6.7278
Max Act: 6.0403. Min Act: -0.1700
Data Index: 8044456 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7278. Min Range: -6.7278
Max Act: 6.0403. Min Act: -0.1700
Data Index: 6429061 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7278. Min Range: -6.7278
Max Act: 6.0403. Min Act: -0.1700
Data Index: 6917400 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7278. Min Range: -6.7278
Max Act: 6.0091. Min Act: -0.1700
Data Index: 6924919 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7278. Min Range: -6.7278
Max Act: 5.9778. Min Act: -0.1700
Data Index: 4829457 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7278. Min Range: -6.7278
Max Act: 5.9778. Min Act: -0.1700
Data Index: 2310470 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7278. Min Range: -6.7278
Max Act: 5.9466. Min Act: -0.1700
Data Index: 1044940 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7278. Min Range: -6.7278
Max Act: 5.9466. Min Act: -0.1700
Data Index: 3054965 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7278. Min Range: -6.7278
Max Act: 5.9153. Min Act: -0.1700
Data Index: 6783906 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7278. Min Range: -6.7278
Max Act: 5.9153. Min Act: -0.1700
Data Index: 6303703 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19