Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4134 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9943. Min Range: -3.9943
Max Act: 3.9943. Min Act: -0.1700
Data Index: 3119286 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9943. Min Range: -3.9943
Max Act: 3.9005. Min Act: -0.1700
Data Index: 4798030 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9943. Min Range: -3.9943
Max Act: 3.8693. Min Act: -0.1700
Data Index: 4633967 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9943. Min Range: -3.9943
Max Act: 3.8693. Min Act: -0.1700
Data Index: 6843289 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9943. Min Range: -3.9943
Max Act: 3.8693. Min Act: -0.1700
Data Index: 6040458 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9943. Min Range: -3.9943
Max Act: 3.8380. Min Act: -0.1700
Data Index: 2145537 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9943. Min Range: -3.9943
Max Act: 3.8380. Min Act: -0.1700
Data Index: 3266546 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9943. Min Range: -3.9943
Max Act: 3.8067. Min Act: -0.1700
Data Index: 2548030 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9943. Min Range: -3.9943
Max Act: 3.7598. Min Act: -0.1700
Data Index: 781900 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9943. Min Range: -3.9943
Max Act: 3.7755. Min Act: -0.1700
Data Index: 996630 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9943. Min Range: -3.9943
Max Act: 3.7598. Min Act: -0.1700
Data Index: 4408737 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9943. Min Range: -3.9943
Max Act: 3.7598. Min Act: -0.1700
Data Index: 1739796 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9943. Min Range: -3.9943
Max Act: 3.7442. Min Act: -0.1700
Data Index: 349393 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9943. Min Range: -3.9943
Max Act: 3.7285. Min Act: -0.1700
Data Index: 1273413 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9943. Min Range: -3.9943
Max Act: 3.7129. Min Act: -0.1700
Data Index: 5027095 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9943. Min Range: -3.9943
Max Act: 3.7285. Min Act: -0.1700
Data Index: 1291054 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9943. Min Range: -3.9943
Max Act: 3.7285. Min Act: -0.1700
Data Index: 1639741 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9943. Min Range: -3.9943
Max Act: 3.6972. Min Act: -0.1700
Data Index: 4012726 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9943. Min Range: -3.9943
Max Act: 3.7285. Min Act: -0.1700
Data Index: 2820489 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9943. Min Range: -3.9943
Max Act: 3.7129. Min Act: -0.1700
Data Index: 186497 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19