Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4069 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1168. Min Range: -4.1168
Max Act: 4.1168. Min Act: -0.1700
Data Index: 8122507 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1168. Min Range: -4.1168
Max Act: 4.1168. Min Act: -0.1700
Data Index: 956208 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1168. Min Range: -4.1168
Max Act: 4.0542. Min Act: -0.1700
Data Index: 7333237 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1168. Min Range: -4.1168
Max Act: 4.0542. Min Act: -0.1700
Data Index: 5220000 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1168. Min Range: -4.1168
Max Act: 4.0230. Min Act: -0.1700
Data Index: 1899082 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1168. Min Range: -4.1168
Max Act: 4.0855. Min Act: -0.1700
Data Index: 6077229 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1168. Min Range: -4.1168
Max Act: 4.0542. Min Act: -0.1700
Data Index: 8720074 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1168. Min Range: -4.1168
Max Act: 4.0230. Min Act: -0.1700
Data Index: 7674630 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1168. Min Range: -4.1168
Max Act: 3.9917. Min Act: -0.1700
Data Index: 5518353 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1168. Min Range: -4.1168
Max Act: 3.9917. Min Act: -0.1700
Data Index: 7425861 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1168. Min Range: -4.1168
Max Act: 4.0230. Min Act: -0.1700
Data Index: 1102502 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1168. Min Range: -4.1168
Max Act: 4.0230. Min Act: -0.1700
Data Index: 2258634 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1168. Min Range: -4.1168
Max Act: 4.0230. Min Act: -0.1700
Data Index: 2478713 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1168. Min Range: -4.1168
Max Act: 4.0230. Min Act: -0.1700
Data Index: 1069627 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1168. Min Range: -4.1168
Max Act: 4.0542. Min Act: -0.1700
Data Index: 1934861 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1168. Min Range: -4.1168
Max Act: 3.9605. Min Act: -0.1700
Data Index: 3617007 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1168. Min Range: -4.1168
Max Act: 3.9917. Min Act: -0.1700
Data Index: 1931479 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1168. Min Range: -4.1168
Max Act: 3.9917. Min Act: -0.1700
Data Index: 2616512 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1168. Min Range: -4.1168
Max Act: 3.9917. Min Act: -0.1700
Data Index: 4553848 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1168. Min Range: -4.1168
Max Act: 3.9917. Min Act: -0.1700
Data Index: 3147004 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19