Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3730 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5631. Min Range: -6.5631
Max Act: 6.5631. Min Act: -0.1700
Data Index: 3696301 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5631. Min Range: -6.5631
Max Act: 6.5631. Min Act: -0.1700
Data Index: 3696300 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5631. Min Range: -6.5631
Max Act: 6.5318. Min Act: -0.1700
Data Index: 22136 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5631. Min Range: -6.5631
Max Act: 6.4693. Min Act: -0.1700
Data Index: 6378909 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5631. Min Range: -6.5631
Max Act: 6.4068. Min Act: -0.1700
Data Index: 5322058 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5631. Min Range: -6.5631
Max Act: 6.4068. Min Act: -0.1700
Data Index: 2113636 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5631. Min Range: -6.5631
Max Act: 6.3756. Min Act: -0.1700
Data Index: 1630204 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5631. Min Range: -6.5631
Max Act: 6.2818. Min Act: -0.1700
Data Index: 2999792 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5631. Min Range: -6.5631
Max Act: 6.3131. Min Act: -0.1700
Data Index: 8387189 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5631. Min Range: -6.5631
Max Act: 6.3131. Min Act: -0.1700
Data Index: 6519311 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5631. Min Range: -6.5631
Max Act: 6.3443. Min Act: -0.1700
Data Index: 2183332 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5631. Min Range: -6.5631
Max Act: 6.3131. Min Act: -0.1700
Data Index: 3481294 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5631. Min Range: -6.5631
Max Act: 6.3131. Min Act: -0.1700
Data Index: 2336306 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5631. Min Range: -6.5631
Max Act: 6.3131. Min Act: -0.1700
Data Index: 6962273 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5631. Min Range: -6.5631
Max Act: 6.2818. Min Act: -0.1700
Data Index: 7037793 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5631. Min Range: -6.5631
Max Act: 6.2818. Min Act: -0.1700
Data Index: 3396540 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5631. Min Range: -6.5631
Max Act: 6.2506. Min Act: -0.1700
Data Index: 6767261 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5631. Min Range: -6.5631
Max Act: 6.2506. Min Act: -0.1700
Data Index: 7024811 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5631. Min Range: -6.5631
Max Act: 6.2193. Min Act: -0.1700
Data Index: 7915982 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5631. Min Range: -6.5631
Max Act: 6.1881. Min Act: -0.1700
Data Index: 3217436 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19