Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2784 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8977. Min Range: -6.8977
Max Act: 6.8977. Min Act: -0.1700
Data Index: 7495852 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8977. Min Range: -6.8977
Max Act: 6.8352. Min Act: -0.1700
Data Index: 745056 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8977. Min Range: -6.8977
Max Act: 6.7727. Min Act: -0.1700
Data Index: 7800135 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8977. Min Range: -6.8977
Max Act: 6.7415. Min Act: -0.1700
Data Index: 4605887 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8977. Min Range: -6.8977
Max Act: 6.7415. Min Act: -0.1700
Data Index: 4530922 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8977. Min Range: -6.8977
Max Act: 6.7102. Min Act: -0.1700
Data Index: 4150949 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8977. Min Range: -6.8977
Max Act: 6.7415. Min Act: -0.1700
Data Index: 6952893 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8977. Min Range: -6.8977
Max Act: 6.7102. Min Act: -0.1700
Data Index: 7585640 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8977. Min Range: -6.8977
Max Act: 6.6790. Min Act: -0.1700
Data Index: 8493713 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8977. Min Range: -6.8977
Max Act: 6.6790. Min Act: -0.1700
Data Index: 8468528 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8977. Min Range: -6.8977
Max Act: 6.6477. Min Act: -0.1700
Data Index: 4248558 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8977. Min Range: -6.8977
Max Act: 6.6477. Min Act: -0.1700
Data Index: 8131005 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8977. Min Range: -6.8977
Max Act: 6.6165. Min Act: -0.1700
Data Index: 3841844 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8977. Min Range: -6.8977
Max Act: 6.5852. Min Act: -0.1700
Data Index: 496794 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8977. Min Range: -6.8977
Max Act: 6.5852. Min Act: -0.1700
Data Index: 2512691 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8977. Min Range: -6.8977
Max Act: 6.5852. Min Act: -0.1700
Data Index: 7769244 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8977. Min Range: -6.8977
Max Act: 6.5540. Min Act: -0.1700
Data Index: 6002123 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8977. Min Range: -6.8977
Max Act: 6.5227. Min Act: -0.1700
Data Index: 1590174 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8977. Min Range: -6.8977
Max Act: 6.5227. Min Act: -0.1700
Data Index: 6763157 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8977. Min Range: -6.8977
Max Act: 6.5227. Min Act: -0.1700
Data Index: 4183306 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19