Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1436 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3913. Min Range: -8.3913
Max Act: 8.3913. Min Act: -0.1700
Data Index: 625097 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3913. Min Range: -8.3913
Max Act: 8.2663. Min Act: -0.1700
Data Index: 7657521 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3913. Min Range: -8.3913
Max Act: 8.0163. Min Act: -0.1700
Data Index: 335480 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3913. Min Range: -8.3913
Max Act: 7.9850. Min Act: -0.1700
Data Index: 1885628 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3913. Min Range: -8.3913
Max Act: 7.9850. Min Act: -0.1700
Data Index: 7057587 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3913. Min Range: -8.3913
Max Act: 7.9538. Min Act: -0.1700
Data Index: 2965422 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3913. Min Range: -8.3913
Max Act: 7.9225. Min Act: -0.1700
Data Index: 8660812 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3913. Min Range: -8.3913
Max Act: 7.8913. Min Act: -0.1700
Data Index: 420618 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3913. Min Range: -8.3913
Max Act: 7.8913. Min Act: -0.1700
Data Index: 2508474 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3913. Min Range: -8.3913
Max Act: 7.8288. Min Act: -0.1700
Data Index: 5823471 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3913. Min Range: -8.3913
Max Act: 7.8600. Min Act: -0.1700
Data Index: 2849160 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3913. Min Range: -8.3913
Max Act: 7.8288. Min Act: -0.1700
Data Index: 2576505 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3913. Min Range: -8.3913
Max Act: 7.8288. Min Act: -0.1700
Data Index: 6588803 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3913. Min Range: -8.3913
Max Act: 7.7350. Min Act: -0.1700
Data Index: 6601154 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3913. Min Range: -8.3913
Max Act: 7.7350. Min Act: -0.1700
Data Index: 7739801 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3913. Min Range: -8.3913
Max Act: 7.7350. Min Act: -0.1700
Data Index: 684286 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3913. Min Range: -8.3913
Max Act: 7.7038. Min Act: -0.1700
Data Index: 6969098 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3913. Min Range: -8.3913
Max Act: 7.6413. Min Act: -0.1700
Data Index: 3469315 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3913. Min Range: -8.3913
Max Act: 7.6725. Min Act: -0.1700
Data Index: 6443574 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3913. Min Range: -8.3913
Max Act: 7.6725. Min Act: -0.1700
Data Index: 1176103 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19