Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1653 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4565. Min Range: -5.4565
Max Act: 5.4565. Min Act: -0.1700
Data Index: 7491633 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4565. Min Range: -5.4565
Max Act: 5.3940. Min Act: -0.1700
Data Index: 8678244 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4565. Min Range: -5.4565
Max Act: 5.3315. Min Act: -0.1700
Data Index: 8270289 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4565. Min Range: -5.4565
Max Act: 5.2065. Min Act: -0.1700
Data Index: 8258832 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4565. Min Range: -5.4565
Max Act: 5.1753. Min Act: -0.1700
Data Index: 4873053 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4565. Min Range: -5.4565
Max Act: 5.1753. Min Act: -0.1700
Data Index: 8678242 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4565. Min Range: -5.4565
Max Act: 5.1440. Min Act: -0.1700
Data Index: 5937023 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4565. Min Range: -5.4565
Max Act: 5.1128. Min Act: -0.1700
Data Index: 5937022 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4565. Min Range: -5.4565
Max Act: 5.1128. Min Act: -0.1700
Data Index: 3241228 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4565. Min Range: -5.4565
Max Act: 5.0815. Min Act: -0.1700
Data Index: 3310575 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4565. Min Range: -5.4565
Max Act: 5.0815. Min Act: -0.1700
Data Index: 2161286 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4565. Min Range: -5.4565
Max Act: 5.0503. Min Act: -0.1700
Data Index: 1682393 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4565. Min Range: -5.4565
Max Act: 5.0190. Min Act: -0.1700
Data Index: 4753642 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4565. Min Range: -5.4565
Max Act: 5.0190. Min Act: -0.1700
Data Index: 7877282 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4565. Min Range: -5.4565
Max Act: 4.9878. Min Act: -0.1700
Data Index: 5421713 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4565. Min Range: -5.4565
Max Act: 4.9565. Min Act: -0.1700
Data Index: 4753643 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4565. Min Range: -5.4565
Max Act: 4.9253. Min Act: -0.1700
Data Index: 5260700 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4565. Min Range: -5.4565
Max Act: 4.8628. Min Act: -0.1700
Data Index: 4238912 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4565. Min Range: -5.4565
Max Act: 4.8628. Min Act: -0.1700
Data Index: 4087944 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4565. Min Range: -5.4565
Max Act: 4.7690. Min Act: -0.1700
Data Index: 1378573 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19