Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3283 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8266. Min Range: -5.8266
Max Act: 5.8266. Min Act: -0.1700
Data Index: 8529358 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8266. Min Range: -5.8266
Max Act: 5.8266. Min Act: -0.1700
Data Index: 1563687 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8266. Min Range: -5.8266
Max Act: 5.7954. Min Act: -0.1700
Data Index: 2594716 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8266. Min Range: -5.8266
Max Act: 5.7954. Min Act: -0.1700
Data Index: 2732863 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8266. Min Range: -5.8266
Max Act: 5.7329. Min Act: -0.1700
Data Index: 2369223 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8266. Min Range: -5.8266
Max Act: 5.7329. Min Act: -0.1700
Data Index: 2186065 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8266. Min Range: -5.8266
Max Act: 5.6704. Min Act: -0.1700
Data Index: 5579042 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8266. Min Range: -5.8266
Max Act: 5.6704. Min Act: -0.1700
Data Index: 4890382 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8266. Min Range: -5.8266
Max Act: 5.6704. Min Act: -0.1700
Data Index: 7959446 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8266. Min Range: -5.8266
Max Act: 5.7016. Min Act: -0.1700
Data Index: 7841473 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8266. Min Range: -5.8266
Max Act: 5.6704. Min Act: -0.1700
Data Index: 6217526 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8266. Min Range: -5.8266
Max Act: 5.6704. Min Act: -0.1700
Data Index: 5957675 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8266. Min Range: -5.8266
Max Act: 5.6704. Min Act: -0.1700
Data Index: 361054 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8266. Min Range: -5.8266
Max Act: 5.6391. Min Act: -0.1700
Data Index: 7099738 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8266. Min Range: -5.8266
Max Act: 5.6079. Min Act: -0.1700
Data Index: 7934444 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8266. Min Range: -5.8266
Max Act: 5.6391. Min Act: -0.1700
Data Index: 1819677 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8266. Min Range: -5.8266
Max Act: 5.6391. Min Act: -0.1700
Data Index: 3447162 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8266. Min Range: -5.8266
Max Act: 5.6391. Min Act: -0.1700
Data Index: 4899150 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8266. Min Range: -5.8266
Max Act: 5.6391. Min Act: -0.1700
Data Index: 5579041 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8266. Min Range: -5.8266
Max Act: 5.6391. Min Act: -0.1700
Data Index: 1656768 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19