Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1081 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1893. Min Range: -9.1893
Max Act: 9.1893. Min Act: -0.1700
Data Index: 3169692 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1893. Min Range: -9.1893
Max Act: 8.8768. Min Act: -0.1700
Data Index: 6409363 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1893. Min Range: -9.1893
Max Act: 8.7518. Min Act: -0.1700
Data Index: 4491757 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1893. Min Range: -9.1893
Max Act: 8.6893. Min Act: -0.1700
Data Index: 6916481 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1893. Min Range: -9.1893
Max Act: 8.6268. Min Act: -0.1700
Data Index: 8102304 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1893. Min Range: -9.1893
Max Act: 8.6268. Min Act: -0.1700
Data Index: 1669995 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1893. Min Range: -9.1893
Max Act: 8.6268. Min Act: -0.1700
Data Index: 1437044 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1893. Min Range: -9.1893
Max Act: 8.5643. Min Act: -0.1700
Data Index: 3488551 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1893. Min Range: -9.1893
Max Act: 8.5018. Min Act: -0.1700
Data Index: 707302 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1893. Min Range: -9.1893
Max Act: 8.5018. Min Act: -0.1700
Data Index: 2197384 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1893. Min Range: -9.1893
Max Act: 8.3768. Min Act: -0.1700
Data Index: 2054491 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1893. Min Range: -9.1893
Max Act: 8.4393. Min Act: -0.1700
Data Index: 7380927 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1893. Min Range: -9.1893
Max Act: 8.3768. Min Act: -0.1700
Data Index: 3646156 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1893. Min Range: -9.1893
Max Act: 8.3768. Min Act: -0.1700
Data Index: 2360792 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1893. Min Range: -9.1893
Max Act: 8.3768. Min Act: -0.1700
Data Index: 8001408 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1893. Min Range: -9.1893
Max Act: 8.3768. Min Act: -0.1700
Data Index: 2479335 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1893. Min Range: -9.1893
Max Act: 8.3768. Min Act: -0.1700
Data Index: 1256178 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1893. Min Range: -9.1893
Max Act: 8.3143. Min Act: -0.1700
Data Index: 2731763 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1893. Min Range: -9.1893
Max Act: 8.3143. Min Act: -0.1700
Data Index: 8099159 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1893. Min Range: -9.1893
Max Act: 8.3143. Min Act: -0.1700
Data Index: 2829995 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19