Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 565 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9258. Min Range: -6.9258
Max Act: 6.9258. Min Act: -0.1700
Data Index: 5095438 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9258. Min Range: -6.9258
Max Act: 6.9258. Min Act: -0.1700
Data Index: 48662 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9258. Min Range: -6.9258
Max Act: 6.8945. Min Act: -0.1700
Data Index: 8580314 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9258. Min Range: -6.9258
Max Act: 6.8633. Min Act: -0.1700
Data Index: 4835615 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9258. Min Range: -6.9258
Max Act: 6.8320. Min Act: -0.1700
Data Index: 5199511 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9258. Min Range: -6.9258
Max Act: 6.8320. Min Act: -0.1700
Data Index: 2954658 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9258. Min Range: -6.9258
Max Act: 6.8320. Min Act: -0.1700
Data Index: 4866754 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9258. Min Range: -6.9258
Max Act: 6.8320. Min Act: -0.1700
Data Index: 3299802 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9258. Min Range: -6.9258
Max Act: 6.8008. Min Act: -0.1700
Data Index: 4429074 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9258. Min Range: -6.9258
Max Act: 6.8008. Min Act: -0.1700
Data Index: 8750726 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9258. Min Range: -6.9258
Max Act: 6.8008. Min Act: -0.1700
Data Index: 3041674 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9258. Min Range: -6.9258
Max Act: 6.7695. Min Act: -0.1700
Data Index: 5796162 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9258. Min Range: -6.9258
Max Act: 6.7695. Min Act: -0.1700
Data Index: 4754473 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9258. Min Range: -6.9258
Max Act: 6.7695. Min Act: -0.1700
Data Index: 4866756 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9258. Min Range: -6.9258
Max Act: 6.7695. Min Act: -0.1700
Data Index: 1155358 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9258. Min Range: -6.9258
Max Act: 6.7695. Min Act: -0.1700
Data Index: 3370841 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9258. Min Range: -6.9258
Max Act: 6.7383. Min Act: -0.1700
Data Index: 5962114 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9258. Min Range: -6.9258
Max Act: 6.7695. Min Act: -0.1700
Data Index: 1933818 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9258. Min Range: -6.9258
Max Act: 6.7383. Min Act: -0.1700
Data Index: 5832359 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9258. Min Range: -6.9258
Max Act: 6.7383. Min Act: -0.1700
Data Index: 6585845 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19