Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5964 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3773. Min Range: -7.3773
Max Act: 7.3773. Min Act: -0.1700
Data Index: 6207870 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3773. Min Range: -7.3773
Max Act: 7.3148. Min Act: -0.1700
Data Index: 8091234 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3773. Min Range: -7.3773
Max Act: 7.2836. Min Act: -0.1700
Data Index: 1516558 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3773. Min Range: -7.3773
Max Act: 7.2523. Min Act: -0.1700
Data Index: 4800024 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3773. Min Range: -7.3773
Max Act: 7.1586. Min Act: -0.1700
Data Index: 2118488 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3773. Min Range: -7.3773
Max Act: 7.0648. Min Act: -0.1700
Data Index: 2378061 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3773. Min Range: -7.3773
Max Act: 7.0023. Min Act: -0.1700
Data Index: 2303509 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3773. Min Range: -7.3773
Max Act: 6.9398. Min Act: -0.1700
Data Index: 904652 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3773. Min Range: -7.3773
Max Act: 6.9086. Min Act: -0.1700
Data Index: 172561 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3773. Min Range: -7.3773
Max Act: 6.8773. Min Act: -0.1700
Data Index: 1150815 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3773. Min Range: -7.3773
Max Act: 6.9086. Min Act: -0.1700
Data Index: 5656554 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3773. Min Range: -7.3773
Max Act: 6.8773. Min Act: -0.1700
Data Index: 643319 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3773. Min Range: -7.3773
Max Act: 6.8773. Min Act: -0.1700
Data Index: 3545022 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3773. Min Range: -7.3773
Max Act: 6.8773. Min Act: -0.1700
Data Index: 6614157 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3773. Min Range: -7.3773
Max Act: 6.8461. Min Act: -0.1700
Data Index: 4725536 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3773. Min Range: -7.3773
Max Act: 6.8148. Min Act: -0.1700
Data Index: 8820484 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3773. Min Range: -7.3773
Max Act: 6.7836. Min Act: -0.1700
Data Index: 1170945 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3773. Min Range: -7.3773
Max Act: 6.7836. Min Act: -0.1700
Data Index: 355528 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3773. Min Range: -7.3773
Max Act: 6.7836. Min Act: -0.1700
Data Index: 842716 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3773. Min Range: -7.3773
Max Act: 6.7836. Min Act: -0.1700
Data Index: 3923203 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19