Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3975 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6177. Min Range: -4.6177
Max Act: 4.6177. Min Act: -0.1700
Data Index: 1208807 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6177. Min Range: -4.6177
Max Act: 4.5864. Min Act: -0.1700
Data Index: 8169185 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6177. Min Range: -4.6177
Max Act: 4.5864. Min Act: -0.1700
Data Index: 3810265 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6177. Min Range: -4.6177
Max Act: 4.5239. Min Act: -0.1700
Data Index: 8009563 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6177. Min Range: -4.6177
Max Act: 4.5239. Min Act: -0.1700
Data Index: 714903 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6177. Min Range: -4.6177
Max Act: 4.5239. Min Act: -0.1700
Data Index: 2353511 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6177. Min Range: -4.6177
Max Act: 4.4927. Min Act: -0.1700
Data Index: 3086861 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6177. Min Range: -4.6177
Max Act: 4.4927. Min Act: -0.1700
Data Index: 2093442 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6177. Min Range: -4.6177
Max Act: 4.4614. Min Act: -0.1700
Data Index: 7250133 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6177. Min Range: -4.6177
Max Act: 4.4302. Min Act: -0.1700
Data Index: 4040999 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6177. Min Range: -4.6177
Max Act: 4.4614. Min Act: -0.1700
Data Index: 1754897 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6177. Min Range: -4.6177
Max Act: 4.4302. Min Act: -0.1700
Data Index: 8513086 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6177. Min Range: -4.6177
Max Act: 4.4302. Min Act: -0.1700
Data Index: 7844138 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6177. Min Range: -4.6177
Max Act: 4.4614. Min Act: -0.1700
Data Index: 5226940 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6177. Min Range: -4.6177
Max Act: 4.3989. Min Act: -0.1700
Data Index: 5232150 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6177. Min Range: -4.6177
Max Act: 4.3677. Min Act: -0.1700
Data Index: 5970029 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6177. Min Range: -4.6177
Max Act: 4.4302. Min Act: -0.1700
Data Index: 1481108 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6177. Min Range: -4.6177
Max Act: 4.3989. Min Act: -0.1700
Data Index: 2825971 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6177. Min Range: -4.6177
Max Act: 4.4614. Min Act: -0.1700
Data Index: 6530504 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6177. Min Range: -4.6177
Max Act: 4.3989. Min Act: -0.1700
Data Index: 1370010 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19