Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3592 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0694. Min Range: -4.0694
Max Act: 4.0694. Min Act: -0.1700
Data Index: 162723 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0694. Min Range: -4.0694
Max Act: 4.0069. Min Act: -0.1700
Data Index: 1620242 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.9444. Min Act: -0.1700
Data Index: 2513198 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.8193. Min Act: -0.1700
Data Index: 5916790 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.8193. Min Act: -0.1700
Data Index: 7332818 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.7724. Min Act: -0.1700
Data Index: 1794399 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.7881. Min Act: -0.1700
Data Index: 2273783 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.7568. Min Act: -0.1700
Data Index: 3664483 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.7881. Min Act: -0.1700
Data Index: 3322894 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.7724. Min Act: -0.1700
Data Index: 4392114 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.7568. Min Act: -0.1700
Data Index: 2514214 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.7411. Min Act: -0.1700
Data Index: 3480666 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.7099. Min Act: -0.1700
Data Index: 3058054 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.7099. Min Act: -0.1700
Data Index: 6112824 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.7255. Min Act: -0.1700
Data Index: 4369188 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.6942. Min Act: -0.1700
Data Index: 6237512 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.6942. Min Act: -0.1700
Data Index: 3650037 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.6629. Min Act: -0.1700
Data Index: 376856 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.6629. Min Act: -0.1700
Data Index: 5207423 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0694. Min Range: -4.0694
Max Act: 3.6316. Min Act: -0.1700
Data Index: 2442782 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19