Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3450 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3546. Min Range: -9.3546
Max Act: 9.3546. Min Act: -0.1700
Data Index: 8520555 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3546. Min Range: -9.3546
Max Act: 9.2921. Min Act: -0.1700
Data Index: 3206266 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3546. Min Range: -9.3546
Max Act: 9.2296. Min Act: -0.1700
Data Index: 948685 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3546. Min Range: -9.3546
Max Act: 9.1671. Min Act: -0.1700
Data Index: 666599 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3546. Min Range: -9.3546
Max Act: 9.1046. Min Act: -0.1700
Data Index: 3748570 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3546. Min Range: -9.3546
Max Act: 8.9796. Min Act: -0.1700
Data Index: 7874909 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3546. Min Range: -9.3546
Max Act: 8.9796. Min Act: -0.1700
Data Index: 18382 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3546. Min Range: -9.3546
Max Act: 8.9796. Min Act: -0.1700
Data Index: 1346684 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3546. Min Range: -9.3546
Max Act: 8.9796. Min Act: -0.1700
Data Index: 5753245 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3546. Min Range: -9.3546
Max Act: 8.9796. Min Act: -0.1700
Data Index: 536366 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3546. Min Range: -9.3546
Max Act: 8.9171. Min Act: -0.1700
Data Index: 1796792 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3546. Min Range: -9.3546
Max Act: 8.9171. Min Act: -0.1700
Data Index: 8082062 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3546. Min Range: -9.3546
Max Act: 8.9171. Min Act: -0.1700
Data Index: 4285250 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3546. Min Range: -9.3546
Max Act: 8.7921. Min Act: -0.1700
Data Index: 3714022 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3546. Min Range: -9.3546
Max Act: 8.7921. Min Act: -0.1700
Data Index: 2601676 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3546. Min Range: -9.3546
Max Act: 8.9171. Min Act: -0.1700
Data Index: 5027781 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3546. Min Range: -9.3546
Max Act: 8.7921. Min Act: -0.1700
Data Index: 2658767 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3546. Min Range: -9.3546
Max Act: 8.7296. Min Act: -0.1700
Data Index: 1232245 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3546. Min Range: -9.3546
Max Act: 8.7296. Min Act: -0.1700
Data Index: 3116983 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3546. Min Range: -9.3546
Max Act: 8.7296. Min Act: -0.1700
Data Index: 8094664 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19