Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 567 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2463. Min Range: -2.2463
Max Act: 2.2463. Min Act: -0.1700
Data Index: 5417853 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2463. Min Range: -2.2463
Max Act: 2.1800. Min Act: -0.1700
Data Index: 5237673 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2463. Min Range: -2.2463
Max Act: 2.1634. Min Act: -0.1700
Data Index: 3007632 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2463. Min Range: -2.2463
Max Act: 2.1467. Min Act: -0.1700
Data Index: 5982928 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2463. Min Range: -2.2463
Max Act: 2.1133. Min Act: -0.1700
Data Index: 5149835 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2463. Min Range: -2.2463
Max Act: 2.1133. Min Act: -0.1700
Data Index: 756957 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2463. Min Range: -2.2463
Max Act: 2.1133. Min Act: -0.1700
Data Index: 7827142 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2463. Min Range: -2.2463
Max Act: 2.0630. Min Act: -0.1700
Data Index: 1376580 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2463. Min Range: -2.2463
Max Act: 2.0798. Min Act: -0.1700
Data Index: 5524951 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2463. Min Range: -2.2463
Max Act: 2.0966. Min Act: -0.1700
Data Index: 4334945 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2463. Min Range: -2.2463
Max Act: 2.0462. Min Act: -0.1700
Data Index: 2992153 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2463. Min Range: -2.2463
Max Act: 2.0630. Min Act: -0.1700
Data Index: 1639318 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2463. Min Range: -2.2463
Max Act: 2.0630. Min Act: -0.1700
Data Index: 3051579 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2463. Min Range: -2.2463
Max Act: 2.0798. Min Act: -0.1700
Data Index: 3187883 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2463. Min Range: -2.2463
Max Act: 2.0798. Min Act: -0.1700
Data Index: 1816409 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2463. Min Range: -2.2463
Max Act: 2.0462. Min Act: -0.1700
Data Index: 6993510 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2463. Min Range: -2.2463
Max Act: 2.0630. Min Act: -0.1700
Data Index: 2624661 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2463. Min Range: -2.2463
Max Act: 2.0294. Min Act: -0.1700
Data Index: 7319646 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2463. Min Range: -2.2463
Max Act: 2.0294. Min Act: -0.1700
Data Index: 4216405 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2463. Min Range: -2.2463
Max Act: 2.0462. Min Act: -0.1700
Data Index: 7689707 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19