Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3097 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3916. Min Range: -5.3916
Max Act: 5.3916. Min Act: -0.1700
Data Index: 2436871 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3916. Min Range: -5.3916
Max Act: 5.2666. Min Act: -0.1700
Data Index: 5815001 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3916. Min Range: -5.3916
Max Act: 5.2354. Min Act: -0.1700
Data Index: 5946076 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3916. Min Range: -5.3916
Max Act: 5.2354. Min Act: -0.1700
Data Index: 7153959 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3916. Min Range: -5.3916
Max Act: 5.2041. Min Act: -0.1700
Data Index: 4815474 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3916. Min Range: -5.3916
Max Act: 5.1416. Min Act: -0.1700
Data Index: 8612444 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3916. Min Range: -5.3916
Max Act: 5.0791. Min Act: -0.1700
Data Index: 6442880 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3916. Min Range: -5.3916
Max Act: 5.0791. Min Act: -0.1700
Data Index: 26457 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3916. Min Range: -5.3916
Max Act: 5.0791. Min Act: -0.1700
Data Index: 5236044 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3916. Min Range: -5.3916
Max Act: 5.0479. Min Act: -0.1700
Data Index: 8150487 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3916. Min Range: -5.3916
Max Act: 5.0479. Min Act: -0.1700
Data Index: 4815473 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3916. Min Range: -5.3916
Max Act: 5.0166. Min Act: -0.1700
Data Index: 8359880 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3916. Min Range: -5.3916
Max Act: 5.0166. Min Act: -0.1700
Data Index: 8372801 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3916. Min Range: -5.3916
Max Act: 5.0166. Min Act: -0.1700
Data Index: 3380523 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3916. Min Range: -5.3916
Max Act: 5.0166. Min Act: -0.1700
Data Index: 8808891 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3916. Min Range: -5.3916
Max Act: 5.0166. Min Act: -0.1700
Data Index: 8725119 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3916. Min Range: -5.3916
Max Act: 5.0166. Min Act: -0.1700
Data Index: 969655 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3916. Min Range: -5.3916
Max Act: 5.0166. Min Act: -0.1700
Data Index: 2770665 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3916. Min Range: -5.3916
Max Act: 4.9854. Min Act: -0.1700
Data Index: 3068478 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3916. Min Range: -5.3916
Max Act: 4.9854. Min Act: -0.1700
Data Index: 969653 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19