Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3186 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4235. Min Range: -10.4235
Max Act: 10.4235. Min Act: -0.1700
Data Index: 6741459 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4235. Min Range: -10.4235
Max Act: 10.0485. Min Act: -0.1700
Data Index: 3069801 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4235. Min Range: -10.4235
Max Act: 9.9235. Min Act: -0.1700
Data Index: 3094810 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4235. Min Range: -10.4235
Max Act: 9.7985. Min Act: -0.1700
Data Index: 6360786 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4235. Min Range: -10.4235
Max Act: 9.7985. Min Act: -0.1700
Data Index: 3069803 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4235. Min Range: -10.4235
Max Act: 9.5485. Min Act: -0.1700
Data Index: 5756751 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4235. Min Range: -10.4235
Max Act: 9.4860. Min Act: -0.1700
Data Index: 669013 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4235. Min Range: -10.4235
Max Act: 9.4860. Min Act: -0.1675
Data Index: 6174381 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4235. Min Range: -10.4235
Max Act: 9.4860. Min Act: -0.1700
Data Index: 2331177 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4235. Min Range: -10.4235
Max Act: 9.4860. Min Act: -0.1700
Data Index: 1130867 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4235. Min Range: -10.4235
Max Act: 9.4235. Min Act: -0.1700
Data Index: 3985946 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4235. Min Range: -10.4235
Max Act: 9.4235. Min Act: -0.1700
Data Index: 1727725 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4235. Min Range: -10.4235
Max Act: 9.4235. Min Act: -0.1700
Data Index: 4208339 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4235. Min Range: -10.4235
Max Act: 9.4235. Min Act: -0.1700
Data Index: 6988856 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4235. Min Range: -10.4235
Max Act: 9.3610. Min Act: -0.1700
Data Index: 3918435 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4235. Min Range: -10.4235
Max Act: 9.3610. Min Act: -0.1700
Data Index: 2832922 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4235. Min Range: -10.4235
Max Act: 9.3610. Min Act: -0.1700
Data Index: 3239971 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4235. Min Range: -10.4235
Max Act: 9.2985. Min Act: -0.1700
Data Index: 1594088 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4235. Min Range: -10.4235
Max Act: 9.3610. Min Act: -0.1700
Data Index: 3069800 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4235. Min Range: -10.4235
Max Act: 9.3610. Min Act: -0.1700
Data Index: 2796714 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19