Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 536 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6341. Min Range: -3.6341
Max Act: 3.6341. Min Act: -0.1700
Data Index: 4766951 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6341. Min Range: -3.6341
Max Act: 3.6028. Min Act: -0.1700
Data Index: 8751495 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6341. Min Range: -3.6341
Max Act: 3.6028. Min Act: -0.1700
Data Index: 8600217 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6341. Min Range: -3.6341
Max Act: 3.5402. Min Act: -0.1700
Data Index: 8002024 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6341. Min Range: -3.6341
Max Act: 3.4619. Min Act: -0.1700
Data Index: 875552 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6341. Min Range: -3.6341
Max Act: 3.4776. Min Act: -0.1700
Data Index: 2553246 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6341. Min Range: -3.6341
Max Act: 3.4932. Min Act: -0.1700
Data Index: 8440072 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6341. Min Range: -3.6341
Max Act: 3.4619. Min Act: -0.1700
Data Index: 3828953 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6341. Min Range: -3.6341
Max Act: 3.4619. Min Act: -0.1700
Data Index: 993554 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6341. Min Range: -3.6341
Max Act: 3.4619. Min Act: -0.1700
Data Index: 1974721 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6341. Min Range: -3.6341
Max Act: 3.4306. Min Act: -0.1700
Data Index: 7807408 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6341. Min Range: -3.6341
Max Act: 3.4462. Min Act: -0.1700
Data Index: 4496798 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6341. Min Range: -3.6341
Max Act: 3.4149. Min Act: -0.1700
Data Index: 7807407 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6341. Min Range: -3.6341
Max Act: 3.4462. Min Act: -0.1700
Data Index: 4984287 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6341. Min Range: -3.6341
Max Act: 3.4462. Min Act: -0.1700
Data Index: 4948287 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6341. Min Range: -3.6341
Max Act: 3.4149. Min Act: -0.1700
Data Index: 2297921 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6341. Min Range: -3.6341
Max Act: 3.4306. Min Act: -0.1700
Data Index: 3225925 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6341. Min Range: -3.6341
Max Act: 3.4306. Min Act: -0.1700
Data Index: 1617283 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6341. Min Range: -3.6341
Max Act: 3.3992. Min Act: -0.1700
Data Index: 938521 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6341. Min Range: -3.6341
Max Act: 3.3835. Min Act: -0.1700
Data Index: 5282970 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19