Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3668 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7225. Min Range: -6.7225
Max Act: 6.7225. Min Act: -0.1700
Data Index: 5947280 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7225. Min Range: -6.7225
Max Act: 6.2537. Min Act: -0.1700
Data Index: 4501793 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7225. Min Range: -6.7225
Max Act: 6.0975. Min Act: -0.1700
Data Index: 6418864 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7225. Min Range: -6.7225
Max Act: 6.0037. Min Act: -0.1700
Data Index: 3191134 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7225. Min Range: -6.7225
Max Act: 5.9412. Min Act: -0.1700
Data Index: 2071441 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7225. Min Range: -6.7225
Max Act: 5.8787. Min Act: -0.1700
Data Index: 2776308 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7225. Min Range: -6.7225
Max Act: 5.8475. Min Act: -0.1700
Data Index: 6815923 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7225. Min Range: -6.7225
Max Act: 5.8162. Min Act: -0.1700
Data Index: 3800206 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7225. Min Range: -6.7225
Max Act: 5.7225. Min Act: -0.1700
Data Index: 6964963 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7225. Min Range: -6.7225
Max Act: 5.7225. Min Act: -0.1700
Data Index: 2899430 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7225. Min Range: -6.7225
Max Act: 5.7225. Min Act: -0.1700
Data Index: 2044492 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7225. Min Range: -6.7225
Max Act: 5.6912. Min Act: -0.1700
Data Index: 991106 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7225. Min Range: -6.7225
Max Act: 5.6912. Min Act: -0.1700
Data Index: 8300521 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7225. Min Range: -6.7225
Max Act: 5.7225. Min Act: -0.1700
Data Index: 1636265 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7225. Min Range: -6.7225
Max Act: 5.6912. Min Act: -0.1700
Data Index: 677308 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7225. Min Range: -6.7225
Max Act: 5.6912. Min Act: -0.1700
Data Index: 7321295 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7225. Min Range: -6.7225
Max Act: 5.6287. Min Act: -0.1700
Data Index: 545152 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7225. Min Range: -6.7225
Max Act: 5.6287. Min Act: -0.1700
Data Index: 977465 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7225. Min Range: -6.7225
Max Act: 5.6287. Min Act: -0.1700
Data Index: 4541871 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7225. Min Range: -6.7225
Max Act: 5.5975. Min Act: -0.1700
Data Index: 95290 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19