Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1212 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8750. Min Range: -3.8750
Max Act: 3.8750. Min Act: -0.1700
Data Index: 2848717 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8750. Min Range: -3.8750
Max Act: 3.8437. Min Act: -0.1700
Data Index: 6766130 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8750. Min Range: -3.8750
Max Act: 3.8437. Min Act: -0.1700
Data Index: 1624843 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8750. Min Range: -3.8750
Max Act: 3.8125. Min Act: -0.1700
Data Index: 6812722 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8750. Min Range: -3.8750
Max Act: 3.8437. Min Act: -0.1700
Data Index: 7303471 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8750. Min Range: -3.8750
Max Act: 3.7812. Min Act: -0.1700
Data Index: 7039882 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8750. Min Range: -3.8750
Max Act: 3.7812. Min Act: -0.1700
Data Index: 4276203 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8750. Min Range: -3.8750
Max Act: 3.8125. Min Act: -0.1700
Data Index: 4510017 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8750. Min Range: -3.8750
Max Act: 3.7499. Min Act: -0.1700
Data Index: 1657237 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8750. Min Range: -3.8750
Max Act: 3.7812. Min Act: -0.1700
Data Index: 7558644 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8750. Min Range: -3.8750
Max Act: 3.7499. Min Act: -0.1700
Data Index: 8513774 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8750. Min Range: -3.8750
Max Act: 3.7499. Min Act: -0.1700
Data Index: 7253810 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8750. Min Range: -3.8750
Max Act: 3.7186. Min Act: -0.1700
Data Index: 537307 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8750. Min Range: -3.8750
Max Act: 3.6873. Min Act: -0.1700
Data Index: 4956285 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8750. Min Range: -3.8750
Max Act: 3.6717. Min Act: -0.1700
Data Index: 2343030 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8750. Min Range: -3.8750
Max Act: 3.6717. Min Act: -0.1700
Data Index: 2436871 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8750. Min Range: -3.8750
Max Act: 3.6717. Min Act: -0.1700
Data Index: 3758565 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8750. Min Range: -3.8750
Max Act: 3.6717. Min Act: -0.1700
Data Index: 5540639 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8750. Min Range: -3.8750
Max Act: 3.6873. Min Act: -0.1700
Data Index: 2056202 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8750. Min Range: -3.8750
Max Act: 3.6561. Min Act: -0.1700
Data Index: 511764 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19