Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5200 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9708. Min Range: -9.9708
Max Act: 9.9708. Min Act: -0.1700
Data Index: 6371079 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9708. Min Range: -9.9708
Max Act: 9.8458. Min Act: -0.1700
Data Index: 6371082 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9708. Min Range: -9.9708
Max Act: 9.7833. Min Act: -0.1700
Data Index: 4890010 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9708. Min Range: -9.9708
Max Act: 9.7208. Min Act: -0.1649
Data Index: 6371080 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9708. Min Range: -9.9708
Max Act: 9.7208. Min Act: -0.1700
Data Index: 1815202 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9708. Min Range: -9.9708
Max Act: 9.5333. Min Act: -0.1700
Data Index: 4453630 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9708. Min Range: -9.9708
Max Act: 9.5958. Min Act: -0.1697
Data Index: 7218733 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9708. Min Range: -9.9708
Max Act: 9.5958. Min Act: -0.1700
Data Index: 4475470 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9708. Min Range: -9.9708
Max Act: 9.5958. Min Act: -0.1688
Data Index: 7587749 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9708. Min Range: -9.9708
Max Act: 9.5958. Min Act: -0.1700
Data Index: 3108048 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9708. Min Range: -9.9708
Max Act: 9.5333. Min Act: -0.1700
Data Index: 3503376 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9708. Min Range: -9.9708
Max Act: 9.4708. Min Act: -0.1692
Data Index: 6371088 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9708. Min Range: -9.9708
Max Act: 9.4708. Min Act: -0.1700
Data Index: 7773831 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9708. Min Range: -9.9708
Max Act: 9.5333. Min Act: -0.1700
Data Index: 1916599 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9708. Min Range: -9.9708
Max Act: 9.4708. Min Act: -0.1700
Data Index: 6058989 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9708. Min Range: -9.9708
Max Act: 9.4708. Min Act: -0.1700
Data Index: 3211314 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9708. Min Range: -9.9708
Max Act: 9.4708. Min Act: -0.1700
Data Index: 4890014 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9708. Min Range: -9.9708
Max Act: 9.4708. Min Act: -0.1697
Data Index: 695606 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9708. Min Range: -9.9708
Max Act: 9.4083. Min Act: -0.1700
Data Index: 3633599 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9708. Min Range: -9.9708
Max Act: 9.4083. Min Act: -0.1700
Data Index: 2337221 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19