Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 709 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.4405. Min Act: -0.1700
Data Index: 458249 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.4405. Min Act: -0.1700
Data Index: 2750329 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.4092. Min Act: -0.1700
Data Index: 4655721 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.3464. Min Act: -0.1700
Data Index: 7078499 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.2994. Min Act: -0.1700
Data Index: 1248263 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.2994. Min Act: -0.1700
Data Index: 3271627 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.2994. Min Act: -0.1700
Data Index: 1129037 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.3151. Min Act: -0.1700
Data Index: 3606708 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.2994. Min Act: -0.1700
Data Index: 1160731 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.2679. Min Act: -0.1700
Data Index: 1213991 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.2679. Min Act: -0.1700
Data Index: 1875652 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.2837. Min Act: -0.1700
Data Index: 8004947 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.2679. Min Act: -0.1700
Data Index: 1800117 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.2837. Min Act: -0.1700
Data Index: 3271633 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.2679. Min Act: -0.1700
Data Index: 5263064 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.2679. Min Act: -0.1700
Data Index: 5450697 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.2522. Min Act: -0.1700
Data Index: 4108667 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.2522. Min Act: -0.1700
Data Index: 8283079 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.2365. Min Act: -0.1700
Data Index: 1689829 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4405. Min Range: -3.4405
Max Act: 3.2522. Min Act: -0.1700
Data Index: 3915879 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #19