Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3485 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3988. Min Range: -7.3988
Max Act: 7.3988. Min Act: -0.1700
Data Index: 2529165 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3988. Min Range: -7.3988
Max Act: 7.3363. Min Act: -0.1700
Data Index: 8684221 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3988. Min Range: -7.3988
Max Act: 6.8988. Min Act: -0.1700
Data Index: 2853722 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3988. Min Range: -7.3988
Max Act: 6.8988. Min Act: -0.1700
Data Index: 3322312 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3988. Min Range: -7.3988
Max Act: 6.7738. Min Act: -0.1700
Data Index: 8814221 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3988. Min Range: -7.3988
Max Act: 6.8050. Min Act: -0.1700
Data Index: 1280763 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3988. Min Range: -7.3988
Max Act: 6.7738. Min Act: -0.1700
Data Index: 2443026 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3988. Min Range: -7.3988
Max Act: 6.7738. Min Act: -0.1700
Data Index: 6465906 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3988. Min Range: -7.3988
Max Act: 6.7113. Min Act: -0.1700
Data Index: 7542304 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3988. Min Range: -7.3988
Max Act: 6.7425. Min Act: -0.1700
Data Index: 4483300 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3988. Min Range: -7.3988
Max Act: 6.7113. Min Act: -0.1700
Data Index: 4061609 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3988. Min Range: -7.3988
Max Act: 6.7113. Min Act: -0.1700
Data Index: 6278725 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3988. Min Range: -7.3988
Max Act: 6.6800. Min Act: -0.1700
Data Index: 4410077 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3988. Min Range: -7.3988
Max Act: 6.6800. Min Act: -0.1700
Data Index: 2845962 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3988. Min Range: -7.3988
Max Act: 6.6488. Min Act: -0.1700
Data Index: 8460035 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3988. Min Range: -7.3988
Max Act: 6.6488. Min Act: -0.1700
Data Index: 4129630 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3988. Min Range: -7.3988
Max Act: 6.6488. Min Act: -0.1700
Data Index: 1510916 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3988. Min Range: -7.3988
Max Act: 6.6488. Min Act: -0.1700
Data Index: 1488983 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3988. Min Range: -7.3988
Max Act: 6.6488. Min Act: -0.1700
Data Index: 1218753 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3988. Min Range: -7.3988
Max Act: 6.6175. Min Act: -0.1700
Data Index: 7419563 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19