Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2308 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0145. Min Range: -3.0145
Max Act: 3.0145. Min Act: -0.1700
Data Index: 5960048 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0145. Min Range: -3.0145
Max Act: 2.8879. Min Act: -0.1700
Data Index: 5757566 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0145. Min Range: -3.0145
Max Act: 2.8243. Min Act: -0.1700
Data Index: 8520594 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0145. Min Range: -3.0145
Max Act: 2.8402. Min Act: -0.1700
Data Index: 5858542 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0145. Min Range: -3.0145
Max Act: 2.7925. Min Act: -0.1700
Data Index: 4794215 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0145. Min Range: -3.0145
Max Act: 2.7925. Min Act: -0.1700
Data Index: 4988404 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0145. Min Range: -3.0145
Max Act: 2.7766. Min Act: -0.1700
Data Index: 5396198 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0145. Min Range: -3.0145
Max Act: 2.7925. Min Act: -0.1700
Data Index: 6402585 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0145. Min Range: -3.0145
Max Act: 2.7766. Min Act: -0.1700
Data Index: 4866528 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0145. Min Range: -3.0145
Max Act: 2.7287. Min Act: -0.1700
Data Index: 8104408 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0145. Min Range: -3.0145
Max Act: 2.7447. Min Act: -0.1700
Data Index: 5529900 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0145. Min Range: -3.0145
Max Act: 2.7127. Min Act: -0.1700
Data Index: 2645951 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0145. Min Range: -3.0145
Max Act: 2.7287. Min Act: -0.1700
Data Index: 1912270 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0145. Min Range: -3.0145
Max Act: 2.7127. Min Act: -0.1700
Data Index: 2200098 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0145. Min Range: -3.0145
Max Act: 2.6967. Min Act: -0.1700
Data Index: 6431042 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0145. Min Range: -3.0145
Max Act: 2.7127. Min Act: -0.1700
Data Index: 4242812 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0145. Min Range: -3.0145
Max Act: 2.7287. Min Act: -0.1700
Data Index: 8798356 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0145. Min Range: -3.0145
Max Act: 2.6807. Min Act: -0.1700
Data Index: 961095 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0145. Min Range: -3.0145
Max Act: 2.6486. Min Act: -0.1700
Data Index: 2860449 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0145. Min Range: -3.0145
Max Act: 2.6647. Min Act: -0.1700
Data Index: 4458065 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #19