Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2101 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0547. Min Range: -4.0547
Max Act: 4.0547. Min Act: -0.1700
Data Index: 4853075 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0547. Min Range: -4.0547
Max Act: 4.0547. Min Act: -0.1700
Data Index: 1305178 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0547. Min Range: -4.0547
Max Act: 4.0235. Min Act: -0.1700
Data Index: 6010680 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.9609. Min Act: -0.1700
Data Index: 7141971 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.9609. Min Act: -0.1700
Data Index: 4638449 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.9297. Min Act: -0.1700
Data Index: 712597 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.9297. Min Act: -0.1700
Data Index: 6190013 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.8984. Min Act: -0.1700
Data Index: 7366319 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.8984. Min Act: -0.1700
Data Index: 2984392 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.8671. Min Act: -0.1700
Data Index: 7800239 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.8359. Min Act: -0.1700
Data Index: 6461386 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.8202. Min Act: -0.1700
Data Index: 5332459 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.8202. Min Act: -0.1700
Data Index: 7831691 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.8202. Min Act: -0.1700
Data Index: 3002467 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.8046. Min Act: -0.1700
Data Index: 2413137 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.8359. Min Act: -0.1700
Data Index: 592664 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.8202. Min Act: -0.1700
Data Index: 1244998 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.8046. Min Act: -0.1700
Data Index: 663273 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.7890. Min Act: -0.1700
Data Index: 6201689 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0547. Min Range: -4.0547
Max Act: 3.7890. Min Act: -0.1700
Data Index: 1885152 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19