Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3262 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1949. Min Range: -8.1949
Max Act: 8.1949. Min Act: -0.1700
Data Index: 4954508 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1949. Min Range: -8.1949
Max Act: 8.1949. Min Act: -0.1700
Data Index: 4954518 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1949. Min Range: -8.1949
Max Act: 7.9761. Min Act: -0.1700
Data Index: 42260 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1949. Min Range: -8.1949
Max Act: 7.4136. Min Act: -0.1700
Data Index: 8276463 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1949. Min Range: -8.1949
Max Act: 7.1011. Min Act: -0.1700
Data Index: 5725162 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1949. Min Range: -8.1949
Max Act: 7.0386. Min Act: -0.1700
Data Index: 6249130 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1949. Min Range: -8.1949
Max Act: 6.9449. Min Act: -0.1700
Data Index: 4513442 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1949. Min Range: -8.1949
Max Act: 6.8511. Min Act: -0.1700
Data Index: 4550775 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1949. Min Range: -8.1949
Max Act: 6.8511. Min Act: -0.1700
Data Index: 141274 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1949. Min Range: -8.1949
Max Act: 6.8199. Min Act: -0.1700
Data Index: 5092188 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1949. Min Range: -8.1949
Max Act: 6.8199. Min Act: -0.1700
Data Index: 1230362 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1949. Min Range: -8.1949
Max Act: 6.7574. Min Act: -0.1700
Data Index: 4710212 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1949. Min Range: -8.1949
Max Act: 6.7574. Min Act: -0.1700
Data Index: 4954507 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1949. Min Range: -8.1949
Max Act: 6.7574. Min Act: -0.1700
Data Index: 5768694 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1949. Min Range: -8.1949
Max Act: 6.6636. Min Act: -0.1700
Data Index: 3433017 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1949. Min Range: -8.1949
Max Act: 6.6636. Min Act: -0.1700
Data Index: 4954517 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1949. Min Range: -8.1949
Max Act: 6.6324. Min Act: -0.1700
Data Index: 4954509 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1949. Min Range: -8.1949
Max Act: 6.7261. Min Act: -0.1700
Data Index: 5243567 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1949. Min Range: -8.1949
Max Act: 6.6949. Min Act: -0.1700
Data Index: 6520602 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1949. Min Range: -8.1949
Max Act: 6.6324. Min Act: -0.1700
Data Index: 5806159 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19