Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3193 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8612. Min Range: -5.8612
Max Act: 5.8612. Min Act: -0.1700
Data Index: 4474384 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8612. Min Range: -5.8612
Max Act: 5.6112. Min Act: -0.1700
Data Index: 4609673 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8612. Min Range: -5.8612
Max Act: 5.6112. Min Act: -0.1700
Data Index: 217447 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8612. Min Range: -5.8612
Max Act: 5.5487. Min Act: -0.1700
Data Index: 4028676 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8612. Min Range: -5.8612
Max Act: 5.5487. Min Act: -0.1700
Data Index: 4912025 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8612. Min Range: -5.8612
Max Act: 5.5487. Min Act: -0.1700
Data Index: 1256164 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8612. Min Range: -5.8612
Max Act: 5.5487. Min Act: -0.1700
Data Index: 4307755 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8612. Min Range: -5.8612
Max Act: 5.5487. Min Act: -0.1700
Data Index: 4733557 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8612. Min Range: -5.8612
Max Act: 5.5487. Min Act: -0.1700
Data Index: 1985982 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8612. Min Range: -5.8612
Max Act: 5.4862. Min Act: -0.1700
Data Index: 7893289 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8612. Min Range: -5.8612
Max Act: 5.4862. Min Act: -0.1700
Data Index: 4890493 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8612. Min Range: -5.8612
Max Act: 5.4550. Min Act: -0.1700
Data Index: 7826432 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8612. Min Range: -5.8612
Max Act: 5.4550. Min Act: -0.1700
Data Index: 8804388 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8612. Min Range: -5.8612
Max Act: 5.4550. Min Act: -0.1700
Data Index: 640078 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8612. Min Range: -5.8612
Max Act: 5.4237. Min Act: -0.1700
Data Index: 4514841 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8612. Min Range: -5.8612
Max Act: 5.4237. Min Act: -0.1700
Data Index: 6837254 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8612. Min Range: -5.8612
Max Act: 5.4237. Min Act: -0.1700
Data Index: 7325879 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8612. Min Range: -5.8612
Max Act: 5.4237. Min Act: -0.1700
Data Index: 4284602 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8612. Min Range: -5.8612
Max Act: 5.4237. Min Act: -0.1700
Data Index: 1336336 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8612. Min Range: -5.8612
Max Act: 5.4237. Min Act: -0.1700
Data Index: 5419462 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19