Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3404 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1238. Min Range: -7.1238
Max Act: 7.1238. Min Act: -0.1700
Data Index: 3962043 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1238. Min Range: -7.1238
Max Act: 7.0925. Min Act: -0.1700
Data Index: 441008 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1238. Min Range: -7.1238
Max Act: 7.0300. Min Act: -0.1700
Data Index: 5722057 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1238. Min Range: -7.1238
Max Act: 7.0300. Min Act: -0.1700
Data Index: 5367692 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.9363. Min Act: -0.1700
Data Index: 2533366 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.9050. Min Act: -0.1700
Data Index: 4950534 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.7800. Min Act: -0.1700
Data Index: 469758 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.7800. Min Act: -0.1700
Data Index: 6209581 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.8113. Min Act: -0.1700
Data Index: 6254361 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.8425. Min Act: -0.1700
Data Index: 3982261 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.8113. Min Act: -0.1700
Data Index: 7403619 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.6863. Min Act: -0.1700
Data Index: 6989487 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.7175. Min Act: -0.1700
Data Index: 4469189 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.7488. Min Act: -0.1700
Data Index: 1317509 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.7800. Min Act: -0.1700
Data Index: 4266734 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.8113. Min Act: -0.1700
Data Index: 5655559 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.6238. Min Act: -0.1700
Data Index: 3443476 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.7175. Min Act: -0.1700
Data Index: 2169602 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.5925. Min Act: -0.1700
Data Index: 7337036 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1238. Min Range: -7.1238
Max Act: 6.5925. Min Act: -0.1700
Data Index: 2585772 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #19