Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2443 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 8.3104. Min Range: -8.3104
Max Act: 8.3104. Min Act: -0.1700
Data Index: 3951597 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3104. Min Range: -8.3104
Max Act: 8.1542. Min Act: -0.1700
Data Index: 5883534 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3104. Min Range: -8.3104
Max Act: 7.9979. Min Act: -0.1700
Data Index: 419232 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3104. Min Range: -8.3104
Max Act: 8.0292. Min Act: -0.1700
Data Index: 3577936 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3104. Min Range: -8.3104
Max Act: 8.0604. Min Act: -0.1700
Data Index: 429295 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3104. Min Range: -8.3104
Max Act: 7.9354. Min Act: -0.1700
Data Index: 4973501 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3104. Min Range: -8.3104
Max Act: 7.9354. Min Act: -0.1700
Data Index: 514813 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3104. Min Range: -8.3104
Max Act: 7.9042. Min Act: -0.1700
Data Index: 2850073 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3104. Min Range: -8.3104
Max Act: 7.8417. Min Act: -0.1700
Data Index: 7999503 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3104. Min Range: -8.3104
Max Act: 7.9667. Min Act: -0.1700
Data Index: 3070257 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3104. Min Range: -8.3104
Max Act: 7.8729. Min Act: -0.1700
Data Index: 5178372 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3104. Min Range: -8.3104
Max Act: 7.9042. Min Act: -0.1700
Data Index: 7231150 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3104. Min Range: -8.3104
Max Act: 7.8417. Min Act: -0.1700
Data Index: 4863864 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3104. Min Range: -8.3104
Max Act: 7.9354. Min Act: -0.1700
Data Index: 8812223 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3104. Min Range: -8.3104
Max Act: 7.8729. Min Act: -0.1700
Data Index: 6664563 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3104. Min Range: -8.3104
Max Act: 7.8417. Min Act: -0.1700
Data Index: 5996381 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3104. Min Range: -8.3104
Max Act: 7.8729. Min Act: -0.1700
Data Index: 4996474 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3104. Min Range: -8.3104
Max Act: 7.8104. Min Act: -0.1700
Data Index: 7386146 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3104. Min Range: -8.3104
Max Act: 7.8417. Min Act: -0.1700
Data Index: 7800537 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3104. Min Range: -8.3104
Max Act: 7.9042. Min Act: -0.1700
Data Index: 3529330 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19