Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2945 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1148. Min Range: -6.1148
Max Act: 6.1148. Min Act: -0.1700
Data Index: 5454923 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1148. Min Range: -6.1148
Max Act: 5.6148. Min Act: -0.1700
Data Index: 6965208 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1148. Min Range: -6.1148
Max Act: 5.5523. Min Act: -0.1700
Data Index: 8659649 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1148. Min Range: -6.1148
Max Act: 5.5210. Min Act: -0.1700
Data Index: 5880304 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1148. Min Range: -6.1148
Max Act: 5.4898. Min Act: -0.1700
Data Index: 4114453 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1148. Min Range: -6.1148
Max Act: 5.4898. Min Act: -0.1700
Data Index: 6905084 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1148. Min Range: -6.1148
Max Act: 5.4585. Min Act: -0.1700
Data Index: 6366183 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1148. Min Range: -6.1148
Max Act: 5.4585. Min Act: -0.1700
Data Index: 6362356 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1148. Min Range: -6.1148
Max Act: 5.4273. Min Act: -0.1700
Data Index: 3563460 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1148. Min Range: -6.1148
Max Act: 5.3960. Min Act: -0.1700
Data Index: 955195 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1148. Min Range: -6.1148
Max Act: 5.3960. Min Act: -0.1700
Data Index: 6889675 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1148. Min Range: -6.1148
Max Act: 5.3960. Min Act: -0.1700
Data Index: 7655853 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1148. Min Range: -6.1148
Max Act: 5.3960. Min Act: -0.1700
Data Index: 5996550 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1148. Min Range: -6.1148
Max Act: 5.3648. Min Act: -0.1700
Data Index: 1502381 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1148. Min Range: -6.1148
Max Act: 5.3023. Min Act: -0.1700
Data Index: 5734938 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1148. Min Range: -6.1148
Max Act: 5.3335. Min Act: -0.1700
Data Index: 5960571 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1148. Min Range: -6.1148
Max Act: 5.3335. Min Act: -0.1700
Data Index: 6378847 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1148. Min Range: -6.1148
Max Act: 5.3335. Min Act: -0.1700
Data Index: 4661229 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1148. Min Range: -6.1148
Max Act: 5.3648. Min Act: -0.1700
Data Index: 3215092 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1148. Min Range: -6.1148
Max Act: 5.3335. Min Act: -0.1700
Data Index: 4110060 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19