Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3496 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3782. Min Range: -5.3782
Max Act: 5.3782. Min Act: -0.1700
Data Index: 8266883 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3782. Min Range: -5.3782
Max Act: 5.2532. Min Act: -0.1700
Data Index: 3706082 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3782. Min Range: -5.3782
Max Act: 5.2532. Min Act: -0.1700
Data Index: 2477187 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3782. Min Range: -5.3782
Max Act: 5.2219. Min Act: -0.1700
Data Index: 6591722 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3782. Min Range: -5.3782
Max Act: 5.2219. Min Act: -0.1700
Data Index: 6247693 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3782. Min Range: -5.3782
Max Act: 5.1907. Min Act: -0.1700
Data Index: 8124134 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3782. Min Range: -5.3782
Max Act: 5.1594. Min Act: -0.1700
Data Index: 526687 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3782. Min Range: -5.3782
Max Act: 5.1907. Min Act: -0.1700
Data Index: 6097348 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3782. Min Range: -5.3782
Max Act: 5.1907. Min Act: -0.1700
Data Index: 3331846 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3782. Min Range: -5.3782
Max Act: 5.1282. Min Act: -0.1700
Data Index: 7571086 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3782. Min Range: -5.3782
Max Act: 5.1282. Min Act: -0.1700
Data Index: 6797361 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3782. Min Range: -5.3782
Max Act: 5.1594. Min Act: -0.1700
Data Index: 3569447 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3782. Min Range: -5.3782
Max Act: 5.1282. Min Act: -0.1700
Data Index: 7982366 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3782. Min Range: -5.3782
Max Act: 5.0969. Min Act: -0.1700
Data Index: 5151382 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3782. Min Range: -5.3782
Max Act: 5.1282. Min Act: -0.1700
Data Index: 691418 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3782. Min Range: -5.3782
Max Act: 5.1282. Min Act: -0.1700
Data Index: 1092296 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3782. Min Range: -5.3782
Max Act: 5.1282. Min Act: -0.1700
Data Index: 5844605 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3782. Min Range: -5.3782
Max Act: 5.0969. Min Act: -0.1700
Data Index: 358049 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3782. Min Range: -5.3782
Max Act: 5.0969. Min Act: -0.1700
Data Index: 6904546 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3782. Min Range: -5.3782
Max Act: 5.0969. Min Act: -0.1700
Data Index: 997151 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19