Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2476 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.4751. Min Act: -0.1700
Data Index: 5548966 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.4751. Min Act: -0.1700
Data Index: 1381877 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.3501. Min Act: -0.1700
Data Index: 895136 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.2876. Min Act: -0.1700
Data Index: 4020165 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.2876. Min Act: -0.1700
Data Index: 6706350 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.2251. Min Act: -0.1700
Data Index: 2615802 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.2251. Min Act: -0.1700
Data Index: 1716313 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.2251. Min Act: -0.1700
Data Index: 7253993 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.1626. Min Act: -0.1700
Data Index: 3259937 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.1939. Min Act: -0.1700
Data Index: 4990241 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.1939. Min Act: -0.1700
Data Index: 2518471 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.1939. Min Act: -0.1700
Data Index: 5957826 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.1626. Min Act: -0.1700
Data Index: 7857487 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.1314. Min Act: -0.1700
Data Index: 4503881 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.1939. Min Act: -0.1700
Data Index: 8611224 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.1314. Min Act: -0.1700
Data Index: 7477764 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.1001. Min Act: -0.1700
Data Index: 8671055 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.1001. Min Act: -0.1700
Data Index: 3892204 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.1001. Min Act: -0.1700
Data Index: 6351001 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.1001. Min Act: -0.1700
Data Index: 5717542 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19