Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1193 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3395. Min Range: -6.3395
Max Act: 6.3395. Min Act: -0.1700
Data Index: 1366343 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3395. Min Range: -6.3395
Max Act: 6.3395. Min Act: -0.1700
Data Index: 7229674 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3395. Min Range: -6.3395
Max Act: 6.2770. Min Act: -0.1700
Data Index: 632693 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3395. Min Range: -6.3395
Max Act: 6.1520. Min Act: -0.1700
Data Index: 1348960 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3395. Min Range: -6.3395
Max Act: 6.1207. Min Act: -0.1700
Data Index: 921629 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3395. Min Range: -6.3395
Max Act: 6.0895. Min Act: -0.1700
Data Index: 3921034 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3395. Min Range: -6.3395
Max Act: 6.0582. Min Act: -0.1700
Data Index: 2287425 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3395. Min Range: -6.3395
Max Act: 6.0270. Min Act: -0.1700
Data Index: 5495669 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3395. Min Range: -6.3395
Max Act: 6.0270. Min Act: -0.1700
Data Index: 7415389 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3395. Min Range: -6.3395
Max Act: 6.0270. Min Act: -0.1700
Data Index: 3967058 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3395. Min Range: -6.3395
Max Act: 5.9957. Min Act: -0.1700
Data Index: 6832203 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3395. Min Range: -6.3395
Max Act: 5.9645. Min Act: -0.1700
Data Index: 5108104 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3395. Min Range: -6.3395
Max Act: 5.9957. Min Act: -0.1700
Data Index: 4323656 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3395. Min Range: -6.3395
Max Act: 5.9645. Min Act: -0.1700
Data Index: 4464370 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3395. Min Range: -6.3395
Max Act: 5.9957. Min Act: -0.1700
Data Index: 6670927 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3395. Min Range: -6.3395
Max Act: 5.9332. Min Act: -0.1700
Data Index: 5148132 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3395. Min Range: -6.3395
Max Act: 5.9645. Min Act: -0.1700
Data Index: 1517277 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3395. Min Range: -6.3395
Max Act: 5.9332. Min Act: -0.1700
Data Index: 2331773 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3395. Min Range: -6.3395
Max Act: 5.9332. Min Act: -0.1700
Data Index: 6601816 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3395. Min Range: -6.3395
Max Act: 5.9020. Min Act: -0.1700
Data Index: 6097102 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19