Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3962 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8660. Min Range: -3.8660
Max Act: 3.8660. Min Act: -0.1700
Data Index: 3190136 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8660. Min Range: -3.8660
Max Act: 3.8660. Min Act: -0.1700
Data Index: 8589692 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8660. Min Range: -3.8660
Max Act: 3.8660. Min Act: -0.1700
Data Index: 4149948 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8660. Min Range: -3.8660
Max Act: 3.7878. Min Act: -0.1700
Data Index: 956874 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8660. Min Range: -3.8660
Max Act: 3.7878. Min Act: -0.1700
Data Index: 1494045 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8660. Min Range: -3.8660
Max Act: 3.7409. Min Act: -0.1700
Data Index: 2101340 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8660. Min Range: -3.8660
Max Act: 3.7252. Min Act: -0.1700
Data Index: 3392008 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8660. Min Range: -3.8660
Max Act: 3.7096. Min Act: -0.1700
Data Index: 313735 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8660. Min Range: -3.8660
Max Act: 3.6783. Min Act: -0.1700
Data Index: 6519355 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8660. Min Range: -3.8660
Max Act: 3.6626. Min Act: -0.1700
Data Index: 5463670 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8660. Min Range: -3.8660
Max Act: 3.6314. Min Act: -0.1700
Data Index: 939758 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8660. Min Range: -3.8660
Max Act: 3.6626. Min Act: -0.1700
Data Index: 6527683 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8660. Min Range: -3.8660
Max Act: 3.6314. Min Act: -0.1700
Data Index: 6844713 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8660. Min Range: -3.8660
Max Act: 3.6001. Min Act: -0.1700
Data Index: 6340246 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8660. Min Range: -3.8660
Max Act: 3.6314. Min Act: -0.1700
Data Index: 5499701 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8660. Min Range: -3.8660
Max Act: 3.6314. Min Act: -0.1700
Data Index: 1851690 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8660. Min Range: -3.8660
Max Act: 3.6470. Min Act: -0.1700
Data Index: 2517776 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8660. Min Range: -3.8660
Max Act: 3.6626. Min Act: -0.1700
Data Index: 4258434 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8660. Min Range: -3.8660
Max Act: 3.6157. Min Act: -0.1700
Data Index: 8359970 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8660. Min Range: -3.8660
Max Act: 3.6470. Min Act: -0.1700
Data Index: 2388009 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19