Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4120 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9287. Min Range: -6.9287
Max Act: 6.9287. Min Act: -0.1700
Data Index: 6857574 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9287. Min Range: -6.9287
Max Act: 6.8974. Min Act: -0.1700
Data Index: 8291673 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9287. Min Range: -6.9287
Max Act: 6.8349. Min Act: -0.1700
Data Index: 3798515 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9287. Min Range: -6.9287
Max Act: 6.7099. Min Act: -0.1700
Data Index: 4952833 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9287. Min Range: -6.9287
Max Act: 6.6787. Min Act: -0.1700
Data Index: 7348355 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9287. Min Range: -6.9287
Max Act: 6.6162. Min Act: -0.1700
Data Index: 8397043 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9287. Min Range: -6.9287
Max Act: 6.5849. Min Act: -0.1700
Data Index: 2664709 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9287. Min Range: -6.9287
Max Act: 6.5849. Min Act: -0.1700
Data Index: 6522023 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9287. Min Range: -6.9287
Max Act: 6.5849. Min Act: -0.1699
Data Index: 7663370 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9287. Min Range: -6.9287
Max Act: 6.5537. Min Act: -0.1700
Data Index: 5980609 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9287. Min Range: -6.9287
Max Act: 6.5537. Min Act: -0.1700
Data Index: 5680381 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9287. Min Range: -6.9287
Max Act: 6.5849. Min Act: -0.1700
Data Index: 6486977 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9287. Min Range: -6.9287
Max Act: 6.5224. Min Act: -0.1700
Data Index: 5332035 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9287. Min Range: -6.9287
Max Act: 6.5224. Min Act: -0.1700
Data Index: 5961949 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9287. Min Range: -6.9287
Max Act: 6.5224. Min Act: -0.1700
Data Index: 2447002 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9287. Min Range: -6.9287
Max Act: 6.4287. Min Act: -0.1700
Data Index: 2470936 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9287. Min Range: -6.9287
Max Act: 6.4287. Min Act: -0.1700
Data Index: 4579163 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9287. Min Range: -6.9287
Max Act: 6.4599. Min Act: -0.1700
Data Index: 3163802 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9287. Min Range: -6.9287
Max Act: 6.4287. Min Act: -0.1700
Data Index: 3618541 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9287. Min Range: -6.9287
Max Act: 6.4599. Min Act: -0.1700
Data Index: 6210888 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19