Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3048 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7489. Min Range: -6.7489
Max Act: 6.7489. Min Act: -0.1700
Data Index: 7154230 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7489. Min Range: -6.7489
Max Act: 6.6864. Min Act: -0.1700
Data Index: 2119122 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7489. Min Range: -6.7489
Max Act: 6.4364. Min Act: -0.1700
Data Index: 72666 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7489. Min Range: -6.7489
Max Act: 6.3427. Min Act: -0.1700
Data Index: 8816529 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7489. Min Range: -6.7489
Max Act: 6.3427. Min Act: -0.1700
Data Index: 4890064 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7489. Min Range: -6.7489
Max Act: 6.3114. Min Act: -0.1700
Data Index: 4422347 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7489. Min Range: -6.7489
Max Act: 6.2802. Min Act: -0.1700
Data Index: 8112915 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7489. Min Range: -6.7489
Max Act: 6.2802. Min Act: -0.1700
Data Index: 4393430 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7489. Min Range: -6.7489
Max Act: 6.2489. Min Act: -0.1700
Data Index: 6163447 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7489. Min Range: -6.7489
Max Act: 6.1864. Min Act: -0.1700
Data Index: 6831569 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7489. Min Range: -6.7489
Max Act: 6.2177. Min Act: -0.1700
Data Index: 8109903 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7489. Min Range: -6.7489
Max Act: 6.2489. Min Act: -0.1700
Data Index: 2637071 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7489. Min Range: -6.7489
Max Act: 6.1864. Min Act: -0.1700
Data Index: 4429648 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7489. Min Range: -6.7489
Max Act: 6.1864. Min Act: -0.1700
Data Index: 5095619 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7489. Min Range: -6.7489
Max Act: 6.1864. Min Act: -0.1700
Data Index: 2224017 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7489. Min Range: -6.7489
Max Act: 6.1552. Min Act: -0.1700
Data Index: 2020237 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7489. Min Range: -6.7489
Max Act: 6.1552. Min Act: -0.1700
Data Index: 2382336 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7489. Min Range: -6.7489
Max Act: 6.1239. Min Act: -0.1700
Data Index: 5796278 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7489. Min Range: -6.7489
Max Act: 6.1552. Min Act: -0.1700
Data Index: 8455431 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7489. Min Range: -6.7489
Max Act: 6.1239. Min Act: -0.1700
Data Index: 6431027 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19