Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 74 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9662. Min Range: -2.9662
Max Act: 2.9662. Min Act: -0.1700
Data Index: 5925643 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9662. Min Range: -2.9662
Max Act: 2.9504. Min Act: -0.1700
Data Index: 8828149 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9662. Min Range: -2.9662
Max Act: 2.9187. Min Act: -0.1700
Data Index: 6324432 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9662. Min Range: -2.9662
Max Act: 2.9345. Min Act: -0.1700
Data Index: 7786682 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9662. Min Range: -2.9662
Max Act: 2.9187. Min Act: -0.1700
Data Index: 7609816 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9662. Min Range: -2.9662
Max Act: 2.9028. Min Act: -0.1700
Data Index: 6790920 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9662. Min Range: -2.9662
Max Act: 2.9028. Min Act: -0.1700
Data Index: 6165947 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9662. Min Range: -2.9662
Max Act: 2.8870. Min Act: -0.1700
Data Index: 6672348 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9662. Min Range: -2.9662
Max Act: 2.8870. Min Act: -0.1700
Data Index: 2911646 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9662. Min Range: -2.9662
Max Act: 2.8552. Min Act: -0.1700
Data Index: 314847 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9662. Min Range: -2.9662
Max Act: 2.8711. Min Act: -0.1700
Data Index: 105977 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9662. Min Range: -2.9662
Max Act: 2.8711. Min Act: -0.1700
Data Index: 7697386 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9662. Min Range: -2.9662
Max Act: 2.8711. Min Act: -0.1700
Data Index: 7554972 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9662. Min Range: -2.9662
Max Act: 2.8711. Min Act: -0.1700
Data Index: 1208418 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9662. Min Range: -2.9662
Max Act: 2.8870. Min Act: -0.1700
Data Index: 302540 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9662. Min Range: -2.9662
Max Act: 2.8552. Min Act: -0.1700
Data Index: 7546704 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9662. Min Range: -2.9662
Max Act: 2.8870. Min Act: -0.1700
Data Index: 7937429 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9662. Min Range: -2.9662
Max Act: 2.8711. Min Act: -0.1700
Data Index: 8599600 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9662. Min Range: -2.9662
Max Act: 2.8870. Min Act: -0.1700
Data Index: 1351021 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9662. Min Range: -2.9662
Max Act: 2.8552. Min Act: -0.1700
Data Index: 4115426 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19