Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1088 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3307. Min Range: -6.3307
Max Act: 6.3307. Min Act: -0.1700
Data Index: 8769396 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3307. Min Range: -6.3307
Max Act: 6.1744. Min Act: -0.1700
Data Index: 6571254 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3307. Min Range: -6.3307
Max Act: 6.1744. Min Act: -0.1700
Data Index: 12228 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3307. Min Range: -6.3307
Max Act: 6.1432. Min Act: -0.1700
Data Index: 3617587 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3307. Min Range: -6.3307
Max Act: 6.1119. Min Act: -0.1700
Data Index: 7920522 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3307. Min Range: -6.3307
Max Act: 6.0494. Min Act: -0.1700
Data Index: 5965922 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3307. Min Range: -6.3307
Max Act: 6.0807. Min Act: -0.1700
Data Index: 838284 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3307. Min Range: -6.3307
Max Act: 6.0494. Min Act: -0.1700
Data Index: 2160002 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3307. Min Range: -6.3307
Max Act: 6.0182. Min Act: -0.1700
Data Index: 7369019 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3307. Min Range: -6.3307
Max Act: 6.0182. Min Act: -0.1700
Data Index: 6713536 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3307. Min Range: -6.3307
Max Act: 5.9557. Min Act: -0.1700
Data Index: 583407 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3307. Min Range: -6.3307
Max Act: 5.9869. Min Act: -0.1700
Data Index: 246481 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3307. Min Range: -6.3307
Max Act: 5.9869. Min Act: -0.1700
Data Index: 3998578 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3307. Min Range: -6.3307
Max Act: 5.9557. Min Act: -0.1700
Data Index: 6058258 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3307. Min Range: -6.3307
Max Act: 5.9869. Min Act: -0.1700
Data Index: 5968191 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3307. Min Range: -6.3307
Max Act: 5.9557. Min Act: -0.1700
Data Index: 4948628 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3307. Min Range: -6.3307
Max Act: 5.9244. Min Act: -0.1700
Data Index: 1432662 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3307. Min Range: -6.3307
Max Act: 5.8932. Min Act: -0.1700
Data Index: 7733055 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3307. Min Range: -6.3307
Max Act: 5.8932. Min Act: -0.1700
Data Index: 5969306 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3307. Min Range: -6.3307
Max Act: 5.8932. Min Act: -0.1700
Data Index: 2864723 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19