Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3687 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2434. Min Range: -6.2434
Max Act: 6.2434. Min Act: -0.1700
Data Index: 5754870 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2434. Min Range: -6.2434
Max Act: 5.9934. Min Act: -0.1700
Data Index: 5802158 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2434. Min Range: -6.2434
Max Act: 5.9622. Min Act: -0.1700
Data Index: 3474357 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2434. Min Range: -6.2434
Max Act: 5.8997. Min Act: -0.1700
Data Index: 6638988 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2434. Min Range: -6.2434
Max Act: 5.8684. Min Act: -0.1700
Data Index: 5806489 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2434. Min Range: -6.2434
Max Act: 5.8372. Min Act: -0.1700
Data Index: 7246249 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2434. Min Range: -6.2434
Max Act: 5.7434. Min Act: -0.1700
Data Index: 5919815 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2434. Min Range: -6.2434
Max Act: 5.7434. Min Act: -0.1700
Data Index: 8474043 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2434. Min Range: -6.2434
Max Act: 5.7122. Min Act: -0.1700
Data Index: 7946513 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2434. Min Range: -6.2434
Max Act: 5.7122. Min Act: -0.1700
Data Index: 2390302 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2434. Min Range: -6.2434
Max Act: 5.7122. Min Act: -0.1700
Data Index: 3743261 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2434. Min Range: -6.2434
Max Act: 5.6809. Min Act: -0.1700
Data Index: 2391998 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2434. Min Range: -6.2434
Max Act: 5.6809. Min Act: -0.1700
Data Index: 6015602 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2434. Min Range: -6.2434
Max Act: 5.6497. Min Act: -0.1700
Data Index: 5340280 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2434. Min Range: -6.2434
Max Act: 5.6809. Min Act: -0.1700
Data Index: 7451375 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2434. Min Range: -6.2434
Max Act: 5.6497. Min Act: -0.1700
Data Index: 4131623 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2434. Min Range: -6.2434
Max Act: 5.6184. Min Act: -0.1700
Data Index: 184760 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2434. Min Range: -6.2434
Max Act: 5.5872. Min Act: -0.1700
Data Index: 8207057 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2434. Min Range: -6.2434
Max Act: 5.5872. Min Act: -0.1700
Data Index: 7720478 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2434. Min Range: -6.2434
Max Act: 5.6184. Min Act: -0.1700
Data Index: 1800498 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19