Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 428 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4466. Min Range: -8.4466
Max Act: 8.4466. Min Act: -0.1700
Data Index: 4642492 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4466. Min Range: -8.4466
Max Act: 8.2591. Min Act: -0.1700
Data Index: 3287186 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4466. Min Range: -8.4466
Max Act: 8.2591. Min Act: -0.1700
Data Index: 5465441 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4466. Min Range: -8.4466
Max Act: 8.2591. Min Act: -0.1700
Data Index: 3375200 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4466. Min Range: -8.4466
Max Act: 8.1341. Min Act: -0.1700
Data Index: 634648 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4466. Min Range: -8.4466
Max Act: 8.0716. Min Act: -0.1700
Data Index: 8715749 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4466. Min Range: -8.4466
Max Act: 8.0716. Min Act: -0.1700
Data Index: 5853196 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4466. Min Range: -8.4466
Max Act: 7.9466. Min Act: -0.1700
Data Index: 4226848 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4466. Min Range: -8.4466
Max Act: 7.9466. Min Act: -0.1700
Data Index: 90204 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4466. Min Range: -8.4466
Max Act: 7.8841. Min Act: -0.1700
Data Index: 1259071 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4466. Min Range: -8.4466
Max Act: 7.8841. Min Act: -0.1700
Data Index: 8563399 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4466. Min Range: -8.4466
Max Act: 7.8841. Min Act: -0.1700
Data Index: 7284643 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4466. Min Range: -8.4466
Max Act: 7.7591. Min Act: -0.1700
Data Index: 8331289 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4466. Min Range: -8.4466
Max Act: 7.7591. Min Act: -0.1700
Data Index: 1665288 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4466. Min Range: -8.4466
Max Act: 7.6341. Min Act: -0.1700
Data Index: 1566751 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4466. Min Range: -8.4466
Max Act: 7.6966. Min Act: -0.1700
Data Index: 5177588 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4466. Min Range: -8.4466
Max Act: 7.6966. Min Act: -0.1700
Data Index: 7316541 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4466. Min Range: -8.4466
Max Act: 7.6966. Min Act: -0.1700
Data Index: 1361288 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4466. Min Range: -8.4466
Max Act: 7.6966. Min Act: -0.1700
Data Index: 2006903 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4466. Min Range: -8.4466
Max Act: 7.6341. Min Act: -0.1700
Data Index: 1663303 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19