Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4747 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1795. Min Range: -6.1795
Max Act: 6.1795. Min Act: -0.1700
Data Index: 3414959 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1795. Min Range: -6.1795
Max Act: 6.0545. Min Act: -0.1700
Data Index: 7228236 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1795. Min Range: -6.1795
Max Act: 6.0232. Min Act: -0.1700
Data Index: 7286028 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1795. Min Range: -6.1795
Max Act: 5.9607. Min Act: -0.1700
Data Index: 4860838 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1795. Min Range: -6.1795
Max Act: 5.9607. Min Act: -0.1700
Data Index: 6847195 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1795. Min Range: -6.1795
Max Act: 5.9607. Min Act: -0.1700
Data Index: 7615562 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1795. Min Range: -6.1795
Max Act: 5.9295. Min Act: -0.1700
Data Index: 7369651 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1795. Min Range: -6.1795
Max Act: 5.9295. Min Act: -0.1700
Data Index: 2308618 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1795. Min Range: -6.1795
Max Act: 5.9295. Min Act: -0.1700
Data Index: 2820376 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1795. Min Range: -6.1795
Max Act: 5.8670. Min Act: -0.1700
Data Index: 3268085 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1795. Min Range: -6.1795
Max Act: 5.8357. Min Act: -0.1700
Data Index: 8793965 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1795. Min Range: -6.1795
Max Act: 5.8670. Min Act: -0.1700
Data Index: 5180763 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1795. Min Range: -6.1795
Max Act: 5.8357. Min Act: -0.1700
Data Index: 4918500 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1795. Min Range: -6.1795
Max Act: 5.8357. Min Act: -0.1700
Data Index: 5341746 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1795. Min Range: -6.1795
Max Act: 5.8045. Min Act: -0.1700
Data Index: 685169 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1795. Min Range: -6.1795
Max Act: 5.8045. Min Act: -0.1700
Data Index: 5428244 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1795. Min Range: -6.1795
Max Act: 5.8045. Min Act: -0.1700
Data Index: 4181626 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1795. Min Range: -6.1795
Max Act: 5.8045. Min Act: -0.1700
Data Index: 7084484 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1795. Min Range: -6.1795
Max Act: 5.7732. Min Act: -0.1700
Data Index: 4805735 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1795. Min Range: -6.1795
Max Act: 5.7732. Min Act: -0.1700
Data Index: 7310334 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19