Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1226 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0326. Min Range: -5.0326
Max Act: 5.0326. Min Act: -0.1700
Data Index: 2985847 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0326. Min Range: -5.0326
Max Act: 5.0014. Min Act: -0.1700
Data Index: 5758239 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0326. Min Range: -5.0326
Max Act: 4.8451. Min Act: -0.1700
Data Index: 7979273 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0326. Min Range: -5.0326
Max Act: 4.7826. Min Act: -0.1700
Data Index: 3964289 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0326. Min Range: -5.0326
Max Act: 4.7201. Min Act: -0.1700
Data Index: 8536075 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0326. Min Range: -5.0326
Max Act: 4.7826. Min Act: -0.1700
Data Index: 611162 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0326. Min Range: -5.0326
Max Act: 4.7514. Min Act: -0.1700
Data Index: 669975 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0326. Min Range: -5.0326
Max Act: 4.7201. Min Act: -0.1700
Data Index: 1443899 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0326. Min Range: -5.0326
Max Act: 4.7201. Min Act: -0.1700
Data Index: 943825 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0326. Min Range: -5.0326
Max Act: 4.6889. Min Act: -0.1700
Data Index: 4016494 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0326. Min Range: -5.0326
Max Act: 4.7201. Min Act: -0.1700
Data Index: 7200092 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0326. Min Range: -5.0326
Max Act: 4.6889. Min Act: -0.1700
Data Index: 2942919 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0326. Min Range: -5.0326
Max Act: 4.6889. Min Act: -0.1700
Data Index: 4730912 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0326. Min Range: -5.0326
Max Act: 4.6889. Min Act: -0.1700
Data Index: 4071245 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0326. Min Range: -5.0326
Max Act: 4.6576. Min Act: -0.1700
Data Index: 4167651 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0326. Min Range: -5.0326
Max Act: 4.6576. Min Act: -0.1700
Data Index: 5684074 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0326. Min Range: -5.0326
Max Act: 4.6576. Min Act: -0.1700
Data Index: 5229647 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0326. Min Range: -5.0326
Max Act: 4.6576. Min Act: -0.1700
Data Index: 5124188 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0326. Min Range: -5.0326
Max Act: 4.6264. Min Act: -0.1700
Data Index: 2450300 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0326. Min Range: -5.0326
Max Act: 4.6264. Min Act: -0.1700
Data Index: 5050597 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19