Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4484 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3614. Min Range: -6.3614
Max Act: 6.3614. Min Act: -0.1700
Data Index: 5462817 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3614. Min Range: -6.3614
Max Act: 6.2989. Min Act: -0.1700
Data Index: 5335689 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3614. Min Range: -6.3614
Max Act: 6.2677. Min Act: -0.1700
Data Index: 7465089 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3614. Min Range: -6.3614
Max Act: 6.2364. Min Act: -0.1700
Data Index: 4293370 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3614. Min Range: -6.3614
Max Act: 6.2364. Min Act: -0.1700
Data Index: 337486 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3614. Min Range: -6.3614
Max Act: 6.2052. Min Act: -0.1700
Data Index: 7586824 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3614. Min Range: -6.3614
Max Act: 6.1739. Min Act: -0.1700
Data Index: 1166495 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3614. Min Range: -6.3614
Max Act: 6.1427. Min Act: -0.1700
Data Index: 3574373 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3614. Min Range: -6.3614
Max Act: 6.1114. Min Act: -0.1700
Data Index: 5886350 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3614. Min Range: -6.3614
Max Act: 6.1114. Min Act: -0.1700
Data Index: 8067942 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3614. Min Range: -6.3614
Max Act: 6.0802. Min Act: -0.1700
Data Index: 4419025 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3614. Min Range: -6.3614
Max Act: 6.0802. Min Act: -0.1700
Data Index: 3973394 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3614. Min Range: -6.3614
Max Act: 6.0802. Min Act: -0.1700
Data Index: 5953289 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3614. Min Range: -6.3614
Max Act: 6.0802. Min Act: -0.1700
Data Index: 3720088 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3614. Min Range: -6.3614
Max Act: 6.0489. Min Act: -0.1700
Data Index: 1954189 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3614. Min Range: -6.3614
Max Act: 6.0489. Min Act: -0.1700
Data Index: 1349139 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3614. Min Range: -6.3614
Max Act: 6.0489. Min Act: -0.1700
Data Index: 3403787 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3614. Min Range: -6.3614
Max Act: 6.0489. Min Act: -0.1700
Data Index: 2043377 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3614. Min Range: -6.3614
Max Act: 6.0489. Min Act: -0.1700
Data Index: 925239 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3614. Min Range: -6.3614
Max Act: 6.0802. Min Act: -0.1700
Data Index: 7989471 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19