Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 625 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3341. Min Range: -6.3341
Max Act: 6.3341. Min Act: -0.1700
Data Index: 7663408 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3341. Min Range: -6.3341
Max Act: 6.3341. Min Act: -0.1700
Data Index: 8175104 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3341. Min Range: -6.3341
Max Act: 6.1778. Min Act: -0.1700
Data Index: 251379 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3341. Min Range: -6.3341
Max Act: 6.1778. Min Act: -0.1700
Data Index: 4472375 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3341. Min Range: -6.3341
Max Act: 6.0841. Min Act: -0.1700
Data Index: 2302406 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3341. Min Range: -6.3341
Max Act: 6.0528. Min Act: -0.1700
Data Index: 2494233 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3341. Min Range: -6.3341
Max Act: 6.0528. Min Act: -0.1700
Data Index: 5611268 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3341. Min Range: -6.3341
Max Act: 6.0528. Min Act: -0.1700
Data Index: 3398191 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3341. Min Range: -6.3341
Max Act: 6.0528. Min Act: -0.1700
Data Index: 4115293 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3341. Min Range: -6.3341
Max Act: 6.0216. Min Act: -0.1700
Data Index: 7718922 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3341. Min Range: -6.3341
Max Act: 6.0216. Min Act: -0.1700
Data Index: 7377399 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3341. Min Range: -6.3341
Max Act: 5.9903. Min Act: -0.1700
Data Index: 4099031 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3341. Min Range: -6.3341
Max Act: 5.9591. Min Act: -0.1700
Data Index: 368010 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3341. Min Range: -6.3341
Max Act: 5.8653. Min Act: -0.1700
Data Index: 543620 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3341. Min Range: -6.3341
Max Act: 5.8653. Min Act: -0.1700
Data Index: 6959420 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3341. Min Range: -6.3341
Max Act: 5.8653. Min Act: -0.1700
Data Index: 1658190 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3341. Min Range: -6.3341
Max Act: 5.8653. Min Act: -0.1700
Data Index: 4597525 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3341. Min Range: -6.3341
Max Act: 5.8341. Min Act: -0.1700
Data Index: 4630172 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3341. Min Range: -6.3341
Max Act: 5.8341. Min Act: -0.1700
Data Index: 4621248 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3341. Min Range: -6.3341
Max Act: 5.8028. Min Act: -0.1700
Data Index: 252667 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19