Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2877 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0882. Min Range: -6.0882
Max Act: 6.0882. Min Act: -0.1700
Data Index: 8568284 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0882. Min Range: -6.0882
Max Act: 6.0257. Min Act: -0.1700
Data Index: 2971781 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0882. Min Range: -6.0882
Max Act: 5.9944. Min Act: -0.1700
Data Index: 4987668 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0882. Min Range: -6.0882
Max Act: 6.0257. Min Act: -0.1700
Data Index: 18127 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0882. Min Range: -6.0882
Max Act: 5.9632. Min Act: -0.1700
Data Index: 3168411 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0882. Min Range: -6.0882
Max Act: 5.8694. Min Act: -0.1700
Data Index: 3784938 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0882. Min Range: -6.0882
Max Act: 5.8382. Min Act: -0.1700
Data Index: 3131880 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0882. Min Range: -6.0882
Max Act: 5.8069. Min Act: -0.1700
Data Index: 5569679 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0882. Min Range: -6.0882
Max Act: 5.8069. Min Act: -0.1700
Data Index: 4441267 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0882. Min Range: -6.0882
Max Act: 5.8069. Min Act: -0.1700
Data Index: 2255106 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0882. Min Range: -6.0882
Max Act: 5.8069. Min Act: -0.1700
Data Index: 4474649 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0882. Min Range: -6.0882
Max Act: 5.7757. Min Act: -0.1700
Data Index: 4406046 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0882. Min Range: -6.0882
Max Act: 5.7757. Min Act: -0.1700
Data Index: 7968673 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0882. Min Range: -6.0882
Max Act: 5.7757. Min Act: -0.1700
Data Index: 1097031 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0882. Min Range: -6.0882
Max Act: 5.7757. Min Act: -0.1700
Data Index: 4804781 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0882. Min Range: -6.0882
Max Act: 5.7757. Min Act: -0.1700
Data Index: 8635802 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0882. Min Range: -6.0882
Max Act: 5.7444. Min Act: -0.1700
Data Index: 5890015 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0882. Min Range: -6.0882
Max Act: 5.7444. Min Act: -0.1700
Data Index: 903371 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0882. Min Range: -6.0882
Max Act: 5.7444. Min Act: -0.1700
Data Index: 6103375 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0882. Min Range: -6.0882
Max Act: 5.7132. Min Act: -0.1700
Data Index: 7566576 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #19