Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1825 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6138. Min Range: -7.6138
Max Act: 7.6138. Min Act: -0.1700
Data Index: 329290 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6138. Min Range: -7.6138
Max Act: 7.4888. Min Act: -0.1700
Data Index: 1651669 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6138. Min Range: -7.6138
Max Act: 7.4576. Min Act: -0.1700
Data Index: 3677842 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6138. Min Range: -7.6138
Max Act: 7.4888. Min Act: -0.1700
Data Index: 4194533 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6138. Min Range: -7.6138
Max Act: 7.4576. Min Act: -0.1700
Data Index: 3897350 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6138. Min Range: -7.6138
Max Act: 7.3951. Min Act: -0.1700
Data Index: 5691801 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6138. Min Range: -7.6138
Max Act: 7.3326. Min Act: -0.1700
Data Index: 71064 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6138. Min Range: -7.6138
Max Act: 7.3326. Min Act: -0.1700
Data Index: 4445831 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6138. Min Range: -7.6138
Max Act: 7.3326. Min Act: -0.1700
Data Index: 5245369 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6138. Min Range: -7.6138
Max Act: 7.3013. Min Act: -0.1700
Data Index: 5138448 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6138. Min Range: -7.6138
Max Act: 7.3013. Min Act: -0.1700
Data Index: 5261195 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6138. Min Range: -7.6138
Max Act: 7.3013. Min Act: -0.1700
Data Index: 5966629 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6138. Min Range: -7.6138
Max Act: 7.3013. Min Act: -0.1700
Data Index: 7923345 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6138. Min Range: -7.6138
Max Act: 7.3013. Min Act: -0.1700
Data Index: 7768652 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6138. Min Range: -7.6138
Max Act: 7.3013. Min Act: -0.1700
Data Index: 7617989 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6138. Min Range: -7.6138
Max Act: 7.3013. Min Act: -0.1700
Data Index: 5930865 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6138. Min Range: -7.6138
Max Act: 7.3013. Min Act: -0.1700
Data Index: 1187604 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6138. Min Range: -7.6138
Max Act: 7.2701. Min Act: -0.1700
Data Index: 7256035 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6138. Min Range: -7.6138
Max Act: 7.2388. Min Act: -0.1700
Data Index: 2257845 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6138. Min Range: -7.6138
Max Act: 7.2701. Min Act: -0.1700
Data Index: 2262799 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19