Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3680 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.5694. Min Act: -0.1700
Data Index: 184526 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.4757. Min Act: -0.1700
Data Index: 3795740 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.4444. Min Act: -0.1700
Data Index: 3795734 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.3194. Min Act: -0.1700
Data Index: 3596438 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.2569. Min Act: -0.1700
Data Index: 2370080 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.2569. Min Act: -0.1700
Data Index: 6912227 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.2256. Min Act: -0.1700
Data Index: 911195 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.2256. Min Act: -0.1700
Data Index: 8384636 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.2569. Min Act: -0.1700
Data Index: 3891886 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.2256. Min Act: -0.1700
Data Index: 2146620 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.1944. Min Act: -0.1700
Data Index: 1033649 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.1944. Min Act: -0.1700
Data Index: 1403890 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.1631. Min Act: -0.1700
Data Index: 3577358 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.1319. Min Act: -0.1700
Data Index: 2925372 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.1631. Min Act: -0.1700
Data Index: 3731762 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.1631. Min Act: -0.1700
Data Index: 348322 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.1631. Min Act: -0.1700
Data Index: 1519813 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.1944. Min Act: -0.1700
Data Index: 4528803 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.1944. Min Act: -0.1700
Data Index: 4528802 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5694. Min Range: -4.5694
Max Act: 4.1631. Min Act: -0.1700
Data Index: 911205 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19