Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 120 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2546. Min Range: -7.2546
Max Act: 7.2546. Min Act: -0.1700
Data Index: 3153377 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2546. Min Range: -7.2546
Max Act: 7.2234. Min Act: -0.1700
Data Index: 6654015 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2546. Min Range: -7.2546
Max Act: 7.1609. Min Act: -0.1700
Data Index: 8802640 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2546. Min Range: -7.2546
Max Act: 7.0671. Min Act: -0.1700
Data Index: 8065992 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2546. Min Range: -7.2546
Max Act: 7.0984. Min Act: -0.1700
Data Index: 5958847 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2546. Min Range: -7.2546
Max Act: 7.0046. Min Act: -0.1700
Data Index: 7329642 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2546. Min Range: -7.2546
Max Act: 6.9734. Min Act: -0.1700
Data Index: 4153178 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2546. Min Range: -7.2546
Max Act: 6.9109. Min Act: -0.1700
Data Index: 6484251 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2546. Min Range: -7.2546
Max Act: 6.8796. Min Act: -0.1700
Data Index: 6132492 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2546. Min Range: -7.2546
Max Act: 6.8796. Min Act: -0.1700
Data Index: 8608171 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2546. Min Range: -7.2546
Max Act: 6.8796. Min Act: -0.1700
Data Index: 8749588 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2546. Min Range: -7.2546
Max Act: 6.8484. Min Act: -0.1700
Data Index: 5323538 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2546. Min Range: -7.2546
Max Act: 6.8484. Min Act: -0.1700
Data Index: 3872878 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2546. Min Range: -7.2546
Max Act: 6.8171. Min Act: -0.1700
Data Index: 5008718 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2546. Min Range: -7.2546
Max Act: 6.8171. Min Act: -0.1700
Data Index: 4924309 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2546. Min Range: -7.2546
Max Act: 6.8171. Min Act: -0.1700
Data Index: 889294 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2546. Min Range: -7.2546
Max Act: 6.8171. Min Act: -0.1700
Data Index: 184539 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2546. Min Range: -7.2546
Max Act: 6.8171. Min Act: -0.1700
Data Index: 8441056 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2546. Min Range: -7.2546
Max Act: 6.7859. Min Act: -0.1700
Data Index: 119309 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2546. Min Range: -7.2546
Max Act: 6.7546. Min Act: -0.1700
Data Index: 8708367 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #19