Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3782 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3147. Min Range: -7.3147
Max Act: 7.3147. Min Act: -0.1700
Data Index: 6043604 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3147. Min Range: -7.3147
Max Act: 7.2522. Min Act: -0.1700
Data Index: 7326686 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3147. Min Range: -7.3147
Max Act: 7.2522. Min Act: -0.1700
Data Index: 6187351 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3147. Min Range: -7.3147
Max Act: 7.2209. Min Act: -0.1700
Data Index: 1015570 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3147. Min Range: -7.3147
Max Act: 7.2209. Min Act: -0.1700
Data Index: 6775139 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3147. Min Range: -7.3147
Max Act: 7.2209. Min Act: -0.1700
Data Index: 2568066 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3147. Min Range: -7.3147
Max Act: 7.1584. Min Act: -0.1700
Data Index: 3921469 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3147. Min Range: -7.3147
Max Act: 7.1584. Min Act: -0.1700
Data Index: 5551365 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3147. Min Range: -7.3147
Max Act: 7.1584. Min Act: -0.1700
Data Index: 7134959 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3147. Min Range: -7.3147
Max Act: 7.1272. Min Act: -0.1700
Data Index: 6979650 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3147. Min Range: -7.3147
Max Act: 7.0959. Min Act: -0.1700
Data Index: 2913923 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3147. Min Range: -7.3147
Max Act: 7.0647. Min Act: -0.1700
Data Index: 131013 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3147. Min Range: -7.3147
Max Act: 7.0959. Min Act: -0.1700
Data Index: 2682424 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3147. Min Range: -7.3147
Max Act: 7.0647. Min Act: -0.1700
Data Index: 3376080 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3147. Min Range: -7.3147
Max Act: 7.0647. Min Act: -0.1700
Data Index: 3207217 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3147. Min Range: -7.3147
Max Act: 7.0647. Min Act: -0.1700
Data Index: 3159325 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3147. Min Range: -7.3147
Max Act: 7.0647. Min Act: -0.1700
Data Index: 1230597 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3147. Min Range: -7.3147
Max Act: 7.0647. Min Act: -0.1700
Data Index: 3246745 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3147. Min Range: -7.3147
Max Act: 7.0647. Min Act: -0.1700
Data Index: 4334917 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3147. Min Range: -7.3147
Max Act: 7.0647. Min Act: -0.1700
Data Index: 2108479 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19