Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4052 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3419. Min Range: -3.3419
Max Act: 3.3419. Min Act: -0.1700
Data Index: 3185951 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3419. Min Range: -3.3419
Max Act: 3.3105. Min Act: -0.1700
Data Index: 284532 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3419. Min Range: -3.3419
Max Act: 3.3105. Min Act: -0.1700
Data Index: 564177 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3419. Min Range: -3.3419
Max Act: 3.3105. Min Act: -0.1700
Data Index: 8617497 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3419. Min Range: -3.3419
Max Act: 3.3105. Min Act: -0.1700
Data Index: 8610116 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3419. Min Range: -3.3419
Max Act: 3.3105. Min Act: -0.1700
Data Index: 1434820 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3419. Min Range: -3.3419
Max Act: 3.2791. Min Act: -0.1700
Data Index: 5417734 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3419. Min Range: -3.3419
Max Act: 3.2791. Min Act: -0.1700
Data Index: 2084226 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3419. Min Range: -3.3419
Max Act: 3.2791. Min Act: -0.1700
Data Index: 8040835 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3419. Min Range: -3.3419
Max Act: 3.2791. Min Act: -0.1700
Data Index: 349838 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3419. Min Range: -3.3419
Max Act: 3.2791. Min Act: -0.1700
Data Index: 7771938 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3419. Min Range: -3.3419
Max Act: 3.2791. Min Act: -0.1700
Data Index: 3810341 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3419. Min Range: -3.3419
Max Act: 3.2791. Min Act: -0.1700
Data Index: 3656030 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3419. Min Range: -3.3419
Max Act: 3.2791. Min Act: -0.1700
Data Index: 7103311 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3419. Min Range: -3.3419
Max Act: 3.2791. Min Act: -0.1700
Data Index: 7039524 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3419. Min Range: -3.3419
Max Act: 3.2791. Min Act: -0.1700
Data Index: 1157035 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3419. Min Range: -3.3419
Max Act: 3.2791. Min Act: -0.1700
Data Index: 6433818 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3419. Min Range: -3.3419
Max Act: 3.2477. Min Act: -0.1700
Data Index: 1887293 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3419. Min Range: -3.3419
Max Act: 3.2477. Min Act: -0.1700
Data Index: 199392 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3419. Min Range: -3.3419
Max Act: 3.2477. Min Act: -0.1700
Data Index: 821288 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19