Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 38 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2292. Min Range: -6.2292
Max Act: 6.2292. Min Act: -0.1700
Data Index: 4682942 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2292. Min Range: -6.2292
Max Act: 6.0729. Min Act: -0.1700
Data Index: 8212738 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2292. Min Range: -6.2292
Max Act: 6.0417. Min Act: -0.1700
Data Index: 3326619 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2292. Min Range: -6.2292
Max Act: 6.0729. Min Act: -0.1696
Data Index: 4490370 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2292. Min Range: -6.2292
Max Act: 6.0417. Min Act: -0.1700
Data Index: 8587636 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2292. Min Range: -6.2292
Max Act: 5.9792. Min Act: -0.1700
Data Index: 4570278 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2292. Min Range: -6.2292
Max Act: 6.0104. Min Act: -0.1700
Data Index: 1697656 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2292. Min Range: -6.2292
Max Act: 5.9792. Min Act: -0.1699
Data Index: 8094981 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2292. Min Range: -6.2292
Max Act: 5.9479. Min Act: -0.1700
Data Index: 1136715 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2292. Min Range: -6.2292
Max Act: 5.9479. Min Act: -0.1700
Data Index: 6429632 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2292. Min Range: -6.2292
Max Act: 5.9167. Min Act: -0.1699
Data Index: 697242 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2292. Min Range: -6.2292
Max Act: 5.9479. Min Act: -0.1700
Data Index: 801282 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2292. Min Range: -6.2292
Max Act: 5.9792. Min Act: -0.1700
Data Index: 2334344 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2292. Min Range: -6.2292
Max Act: 5.9479. Min Act: -0.1700
Data Index: 4105666 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2292. Min Range: -6.2292
Max Act: 5.8854. Min Act: -0.1700
Data Index: 3390898 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2292. Min Range: -6.2292
Max Act: 5.8854. Min Act: -0.1699
Data Index: 6167219 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2292. Min Range: -6.2292
Max Act: 5.9167. Min Act: -0.1700
Data Index: 7255497 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2292. Min Range: -6.2292
Max Act: 5.9167. Min Act: -0.1700
Data Index: 1909089 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2292. Min Range: -6.2292
Max Act: 5.9167. Min Act: -0.1700
Data Index: 8076919 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2292. Min Range: -6.2292
Max Act: 5.8542. Min Act: -0.1700
Data Index: 2273800 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19