Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 32 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.9549. Min Act: -0.1700
Data Index: 6677632 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.9549. Min Act: -0.1700
Data Index: 5918770 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.8756. Min Act: -0.1700
Data Index: 133471 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.8439. Min Act: -0.1700
Data Index: 5815792 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.8121. Min Act: -0.1700
Data Index: 648767 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.8280. Min Act: -0.1700
Data Index: 5697781 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7802. Min Act: -0.1700
Data Index: 1027088 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7961. Min Act: -0.1700
Data Index: 4535863 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7802. Min Act: -0.1700
Data Index: 7480751 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7802. Min Act: -0.1700
Data Index: 5485495 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7802. Min Act: -0.1700
Data Index: 6410987 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7643. Min Act: -0.1700
Data Index: 4186316 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7802. Min Act: -0.1700
Data Index: 8334613 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7643. Min Act: -0.1700
Data Index: 12141 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7643. Min Act: -0.1700
Data Index: 5054999 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7643. Min Act: -0.1700
Data Index: 8591733 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7643. Min Act: -0.1700
Data Index: 6224363 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7643. Min Act: -0.1700
Data Index: 2556273 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7483. Min Act: -0.1700
Data Index: 233116 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7483. Min Act: -0.1700
Data Index: 4375944 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19