Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3242 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4592. Min Range: -4.4592
Max Act: 4.4592. Min Act: -0.1700
Data Index: 6633459 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4592. Min Range: -4.4592
Max Act: 4.4279. Min Act: -0.1700
Data Index: 6097401 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4592. Min Range: -4.4592
Max Act: 4.3654. Min Act: -0.1700
Data Index: 7887417 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4592. Min Range: -4.4592
Max Act: 4.3654. Min Act: -0.1700
Data Index: 8485330 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4592. Min Range: -4.4592
Max Act: 4.3342. Min Act: -0.1700
Data Index: 6171435 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4592. Min Range: -4.4592
Max Act: 4.3342. Min Act: -0.1700
Data Index: 8469096 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4592. Min Range: -4.4592
Max Act: 4.3342. Min Act: -0.1700
Data Index: 8193343 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4592. Min Range: -4.4592
Max Act: 4.3029. Min Act: -0.1700
Data Index: 1444244 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4592. Min Range: -4.4592
Max Act: 4.3029. Min Act: -0.1700
Data Index: 4968876 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4592. Min Range: -4.4592
Max Act: 4.3029. Min Act: -0.1700
Data Index: 2719031 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4592. Min Range: -4.4592
Max Act: 4.3029. Min Act: -0.1700
Data Index: 3997377 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4592. Min Range: -4.4592
Max Act: 4.3029. Min Act: -0.1700
Data Index: 3949442 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4592. Min Range: -4.4592
Max Act: 4.3029. Min Act: -0.1696
Data Index: 620006 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4592. Min Range: -4.4592
Max Act: 4.3029. Min Act: -0.1700
Data Index: 3641762 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4592. Min Range: -4.4592
Max Act: 4.3029. Min Act: -0.1700
Data Index: 6456652 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4592. Min Range: -4.4592
Max Act: 4.3029. Min Act: -0.1700
Data Index: 2069370 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4592. Min Range: -4.4592
Max Act: 4.2717. Min Act: -0.1700
Data Index: 5995010 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4592. Min Range: -4.4592
Max Act: 4.3029. Min Act: -0.1700
Data Index: 5991261 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4592. Min Range: -4.4592
Max Act: 4.2717. Min Act: -0.1700
Data Index: 2735673 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4592. Min Range: -4.4592
Max Act: 4.2717. Min Act: -0.1700
Data Index: 4700199 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19