Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1669 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2573. Min Range: -4.2573
Max Act: 4.2573. Min Act: -0.1700
Data Index: 6184518 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2573. Min Range: -4.2573
Max Act: 4.2573. Min Act: -0.1700
Data Index: 5178762 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2573. Min Range: -4.2573
Max Act: 4.2260. Min Act: -0.1700
Data Index: 5937681 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2573. Min Range: -4.2573
Max Act: 4.1947. Min Act: -0.1700
Data Index: 5469112 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2573. Min Range: -4.2573
Max Act: 4.1010. Min Act: -0.1700
Data Index: 7352526 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2573. Min Range: -4.2573
Max Act: 4.1010. Min Act: -0.1700
Data Index: 6105553 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2573. Min Range: -4.2573
Max Act: 4.1322. Min Act: -0.1700
Data Index: 7573499 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2573. Min Range: -4.2573
Max Act: 4.1010. Min Act: -0.1700
Data Index: 6048889 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2573. Min Range: -4.2573
Max Act: 4.1010. Min Act: -0.1700
Data Index: 1863735 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2573. Min Range: -4.2573
Max Act: 4.0697. Min Act: -0.1700
Data Index: 8808920 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2573. Min Range: -4.2573
Max Act: 4.1010. Min Act: -0.1700
Data Index: 4142611 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2573. Min Range: -4.2573
Max Act: 4.0697. Min Act: -0.1700
Data Index: 5181177 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2573. Min Range: -4.2573
Max Act: 4.0697. Min Act: -0.1700
Data Index: 5038375 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2573. Min Range: -4.2573
Max Act: 4.0385. Min Act: -0.1700
Data Index: 2811625 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2573. Min Range: -4.2573
Max Act: 4.0385. Min Act: -0.1700
Data Index: 6418538 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2573. Min Range: -4.2573
Max Act: 4.0385. Min Act: -0.1700
Data Index: 2303310 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2573. Min Range: -4.2573
Max Act: 4.0385. Min Act: -0.1700
Data Index: 516112 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2573. Min Range: -4.2573
Max Act: 4.0697. Min Act: -0.1700
Data Index: 2982164 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2573. Min Range: -4.2573
Max Act: 4.0385. Min Act: -0.1700
Data Index: 7843347 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2573. Min Range: -4.2573
Max Act: 4.0385. Min Act: -0.1700
Data Index: 5891450 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19