Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3284 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6163. Min Range: -6.6163
Max Act: 6.6163. Min Act: -0.1700
Data Index: 5551438 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6163. Min Range: -6.6163
Max Act: 6.4601. Min Act: -0.1700
Data Index: 3802454 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6163. Min Range: -6.6163
Max Act: 6.3976. Min Act: -0.1700
Data Index: 3431503 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6163. Min Range: -6.6163
Max Act: 6.3663. Min Act: -0.1700
Data Index: 7361656 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6163. Min Range: -6.6163
Max Act: 6.3663. Min Act: -0.1700
Data Index: 4995913 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6163. Min Range: -6.6163
Max Act: 6.3351. Min Act: -0.1700
Data Index: 7211592 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6163. Min Range: -6.6163
Max Act: 6.2726. Min Act: -0.1700
Data Index: 8455282 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6163. Min Range: -6.6163
Max Act: 6.3038. Min Act: -0.1700
Data Index: 3829906 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6163. Min Range: -6.6163
Max Act: 6.2413. Min Act: -0.1700
Data Index: 4072319 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6163. Min Range: -6.6163
Max Act: 6.2101. Min Act: -0.1700
Data Index: 6940387 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6163. Min Range: -6.6163
Max Act: 6.1788. Min Act: -0.1700
Data Index: 3311009 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6163. Min Range: -6.6163
Max Act: 6.1788. Min Act: -0.1700
Data Index: 4090676 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6163. Min Range: -6.6163
Max Act: 6.1788. Min Act: -0.1700
Data Index: 5256747 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6163. Min Range: -6.6163
Max Act: 6.1476. Min Act: -0.1700
Data Index: 8422736 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6163. Min Range: -6.6163
Max Act: 6.1476. Min Act: -0.1700
Data Index: 1503340 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6163. Min Range: -6.6163
Max Act: 6.1476. Min Act: -0.1700
Data Index: 8547674 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6163. Min Range: -6.6163
Max Act: 6.1476. Min Act: -0.1700
Data Index: 2118411 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6163. Min Range: -6.6163
Max Act: 6.1476. Min Act: -0.1700
Data Index: 5893599 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6163. Min Range: -6.6163
Max Act: 6.1163. Min Act: -0.1700
Data Index: 6498035 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6163. Min Range: -6.6163
Max Act: 6.1163. Min Act: -0.1700
Data Index: 3053391 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19