Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6355 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0782. Min Range: -5.0782
Max Act: 5.0782. Min Act: -0.1700
Data Index: 6203745 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0782. Min Range: -5.0782
Max Act: 5.0782. Min Act: -0.1700
Data Index: 7802998 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0782. Min Range: -5.0782
Max Act: 5.0157. Min Act: -0.1700
Data Index: 1668942 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0782. Min Range: -5.0782
Max Act: 4.8907. Min Act: -0.1700
Data Index: 4981091 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0782. Min Range: -5.0782
Max Act: 4.9219. Min Act: -0.1700
Data Index: 3445890 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0782. Min Range: -5.0782
Max Act: 4.8907. Min Act: -0.1700
Data Index: 5078345 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0782. Min Range: -5.0782
Max Act: 4.8594. Min Act: -0.1700
Data Index: 4417000 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0782. Min Range: -5.0782
Max Act: 4.8594. Min Act: -0.1700
Data Index: 7843689 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0782. Min Range: -5.0782
Max Act: 4.8282. Min Act: -0.1700
Data Index: 5643583 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0782. Min Range: -5.0782
Max Act: 4.8282. Min Act: -0.1700
Data Index: 1967994 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0782. Min Range: -5.0782
Max Act: 4.8282. Min Act: -0.1700
Data Index: 5651309 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0782. Min Range: -5.0782
Max Act: 4.7657. Min Act: -0.1700
Data Index: 2818275 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0782. Min Range: -5.0782
Max Act: 4.7969. Min Act: -0.1700
Data Index: 4334201 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0782. Min Range: -5.0782
Max Act: 4.7969. Min Act: -0.1700
Data Index: 7602745 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0782. Min Range: -5.0782
Max Act: 4.7969. Min Act: -0.1700
Data Index: 6620354 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0782. Min Range: -5.0782
Max Act: 4.7969. Min Act: -0.1700
Data Index: 8609832 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0782. Min Range: -5.0782
Max Act: 4.7969. Min Act: -0.1700
Data Index: 4739491 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0782. Min Range: -5.0782
Max Act: 4.7969. Min Act: -0.1700
Data Index: 560724 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0782. Min Range: -5.0782
Max Act: 4.7969. Min Act: -0.1700
Data Index: 72517 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0782. Min Range: -5.0782
Max Act: 4.7969. Min Act: -0.1700
Data Index: 2983827 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #19