Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 827 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.8369. Min Range: -9.8369
Max Act: 9.8369. Min Act: -0.1700
Data Index: 5343459 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8369. Min Range: -9.8369
Max Act: 9.3994. Min Act: -0.1700
Data Index: 5813985 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8369. Min Range: -9.8369
Max Act: 9.2744. Min Act: -0.1700
Data Index: 4914617 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8369. Min Range: -9.8369
Max Act: 9.2119. Min Act: -0.1700
Data Index: 656790 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8369. Min Range: -9.8369
Max Act: 9.1494. Min Act: -0.1700
Data Index: 1663640 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8369. Min Range: -9.8369
Max Act: 9.0869. Min Act: -0.1700
Data Index: 6713985 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8369. Min Range: -9.8369
Max Act: 8.9619. Min Act: -0.1700
Data Index: 2733051 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8369. Min Range: -9.8369
Max Act: 8.9619. Min Act: -0.1700
Data Index: 3058588 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8369. Min Range: -9.8369
Max Act: 8.9619. Min Act: -0.1700
Data Index: 4483669 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8369. Min Range: -9.8369
Max Act: 8.9619. Min Act: -0.1700
Data Index: 103237 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8369. Min Range: -9.8369
Max Act: 8.9619. Min Act: -0.1700
Data Index: 8375794 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8369. Min Range: -9.8369
Max Act: 8.9619. Min Act: -0.1700
Data Index: 293761 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8369. Min Range: -9.8369
Max Act: 8.8369. Min Act: -0.1700
Data Index: 8439148 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8369. Min Range: -9.8369
Max Act: 8.8369. Min Act: -0.1700
Data Index: 1800794 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8369. Min Range: -9.8369
Max Act: 8.8369. Min Act: -0.1700
Data Index: 8146020 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8369. Min Range: -9.8369
Max Act: 8.7744. Min Act: -0.1700
Data Index: 3176442 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8369. Min Range: -9.8369
Max Act: 8.7119. Min Act: -0.1700
Data Index: 6162371 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8369. Min Range: -9.8369
Max Act: 8.8369. Min Act: -0.1700
Data Index: 7947904 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8369. Min Range: -9.8369
Max Act: 8.7119. Min Act: -0.1700
Data Index: 8080749 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8369. Min Range: -9.8369
Max Act: 8.7744. Min Act: -0.1700
Data Index: 5446119 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19