Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5997 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0295. Min Range: -6.0295
Max Act: 6.0295. Min Act: -0.1700
Data Index: 8178698 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0295. Min Range: -6.0295
Max Act: 5.9983. Min Act: -0.1700
Data Index: 315683 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0295. Min Range: -6.0295
Max Act: 5.9670. Min Act: -0.1700
Data Index: 7100586 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0295. Min Range: -6.0295
Max Act: 5.8420. Min Act: -0.1700
Data Index: 1882990 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0295. Min Range: -6.0295
Max Act: 5.8420. Min Act: -0.1700
Data Index: 3704362 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0295. Min Range: -6.0295
Max Act: 5.8420. Min Act: -0.1700
Data Index: 683477 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0295. Min Range: -6.0295
Max Act: 5.8420. Min Act: -0.1700
Data Index: 4471513 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0295. Min Range: -6.0295
Max Act: 5.8108. Min Act: -0.1700
Data Index: 5180559 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0295. Min Range: -6.0295
Max Act: 5.7795. Min Act: -0.1700
Data Index: 2631537 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0295. Min Range: -6.0295
Max Act: 5.7795. Min Act: -0.1700
Data Index: 5664023 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0295. Min Range: -6.0295
Max Act: 5.7483. Min Act: -0.1700
Data Index: 8659241 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0295. Min Range: -6.0295
Max Act: 5.7170. Min Act: -0.1700
Data Index: 8821399 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0295. Min Range: -6.0295
Max Act: 5.7170. Min Act: -0.1700
Data Index: 5249592 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0295. Min Range: -6.0295
Max Act: 5.7170. Min Act: -0.1700
Data Index: 6616617 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0295. Min Range: -6.0295
Max Act: 5.6545. Min Act: -0.1700
Data Index: 3282686 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0295. Min Range: -6.0295
Max Act: 5.6233. Min Act: -0.1700
Data Index: 7055846 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0295. Min Range: -6.0295
Max Act: 5.6545. Min Act: -0.1700
Data Index: 5563404 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0295. Min Range: -6.0295
Max Act: 5.6545. Min Act: -0.1700
Data Index: 8273740 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0295. Min Range: -6.0295
Max Act: 5.6545. Min Act: -0.1700
Data Index: 7102056 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0295. Min Range: -6.0295
Max Act: 5.6545. Min Act: -0.1700
Data Index: 2931835 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19