Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4758 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6194. Min Range: -3.6194
Max Act: 3.6194. Min Act: -0.1700
Data Index: 1130285 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6194. Min Range: -3.6194
Max Act: 3.6037. Min Act: -0.1700
Data Index: 7950109 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6194. Min Range: -3.6194
Max Act: 3.6037. Min Act: -0.1700
Data Index: 5070666 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6194. Min Range: -3.6194
Max Act: 3.5724. Min Act: -0.1700
Data Index: 4543582 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6194. Min Range: -3.6194
Max Act: 3.5411. Min Act: -0.1700
Data Index: 6628800 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6194. Min Range: -3.6194
Max Act: 3.4784. Min Act: -0.1700
Data Index: 2335644 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6194. Min Range: -3.6194
Max Act: 3.4941. Min Act: -0.1700
Data Index: 1175928 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6194. Min Range: -3.6194
Max Act: 3.4784. Min Act: -0.1700
Data Index: 7388322 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6194. Min Range: -3.6194
Max Act: 3.4471. Min Act: -0.1700
Data Index: 7192287 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6194. Min Range: -3.6194
Max Act: 3.4471. Min Act: -0.1700
Data Index: 1593186 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6194. Min Range: -3.6194
Max Act: 3.4158. Min Act: -0.1700
Data Index: 947748 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6194. Min Range: -3.6194
Max Act: 3.4001. Min Act: -0.1700
Data Index: 3687023 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6194. Min Range: -3.6194
Max Act: 3.4158. Min Act: -0.1700
Data Index: 8034031 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6194. Min Range: -3.6194
Max Act: 3.4001. Min Act: -0.1700
Data Index: 3616850 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6194. Min Range: -3.6194
Max Act: 3.3687. Min Act: -0.1700
Data Index: 6996347 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6194. Min Range: -3.6194
Max Act: 3.3687. Min Act: -0.1700
Data Index: 2761953 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6194. Min Range: -3.6194
Max Act: 3.3530. Min Act: -0.1700
Data Index: 2635401 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6194. Min Range: -3.6194
Max Act: 3.3060. Min Act: -0.1700
Data Index: 4851219 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6194. Min Range: -3.6194
Max Act: 3.3060. Min Act: -0.1700
Data Index: 893623 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6194. Min Range: -3.6194
Max Act: 3.3060. Min Act: -0.1700
Data Index: 2797768 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19