Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2971 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8565. Min Range: -6.8565
Max Act: 6.8565. Min Act: -0.1700
Data Index: 2770924 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8565. Min Range: -6.8565
Max Act: 6.7628. Min Act: -0.1700
Data Index: 4920011 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8565. Min Range: -6.8565
Max Act: 6.7315. Min Act: -0.1700
Data Index: 5375952 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8565. Min Range: -6.8565
Max Act: 6.7003. Min Act: -0.1700
Data Index: 3228500 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8565. Min Range: -6.8565
Max Act: 6.6065. Min Act: -0.1700
Data Index: 7616735 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8565. Min Range: -6.8565
Max Act: 6.5753. Min Act: -0.1700
Data Index: 6924683 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8565. Min Range: -6.8565
Max Act: 6.5753. Min Act: -0.1700
Data Index: 5609661 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8565. Min Range: -6.8565
Max Act: 6.6065. Min Act: -0.1700
Data Index: 8101142 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8565. Min Range: -6.8565
Max Act: 6.5753. Min Act: -0.1700
Data Index: 3320974 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8565. Min Range: -6.8565
Max Act: 6.5440. Min Act: -0.1700
Data Index: 6488711 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8565. Min Range: -6.8565
Max Act: 6.5440. Min Act: -0.1700
Data Index: 5289002 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8565. Min Range: -6.8565
Max Act: 6.5128. Min Act: -0.1700
Data Index: 941367 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8565. Min Range: -6.8565
Max Act: 6.5128. Min Act: -0.1700
Data Index: 6629627 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8565. Min Range: -6.8565
Max Act: 6.4815. Min Act: -0.1700
Data Index: 1360939 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8565. Min Range: -6.8565
Max Act: 6.4503. Min Act: -0.1700
Data Index: 2067251 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8565. Min Range: -6.8565
Max Act: 6.4815. Min Act: -0.1700
Data Index: 3182724 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8565. Min Range: -6.8565
Max Act: 6.4503. Min Act: -0.1700
Data Index: 6348728 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8565. Min Range: -6.8565
Max Act: 6.4503. Min Act: -0.1700
Data Index: 3663332 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8565. Min Range: -6.8565
Max Act: 6.4190. Min Act: -0.1700
Data Index: 3005758 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8565. Min Range: -6.8565
Max Act: 6.4503. Min Act: -0.1700
Data Index: 4095131 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19