Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3038 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.9687. Min Act: -0.1700
Data Index: 1419357 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.9062. Min Act: -0.1700
Data Index: 8818829 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.8593. Min Act: -0.1700
Data Index: 615726 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.8437. Min Act: -0.1700
Data Index: 8818831 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.8280. Min Act: -0.1700
Data Index: 2619767 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.8437. Min Act: -0.1700
Data Index: 2707490 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.8437. Min Act: -0.1700
Data Index: 5961500 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.8280. Min Act: -0.1700
Data Index: 2024862 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.8124. Min Act: -0.1700
Data Index: 1074794 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.8124. Min Act: -0.1700
Data Index: 1761958 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.8124. Min Act: -0.1700
Data Index: 3855141 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.8124. Min Act: -0.1700
Data Index: 5342433 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.7968. Min Act: -0.1700
Data Index: 7163208 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.7811. Min Act: -0.1700
Data Index: 159602 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.7968. Min Act: -0.1700
Data Index: 4352207 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.7968. Min Act: -0.1700
Data Index: 7715543 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.8124. Min Act: -0.1700
Data Index: 8321526 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.7968. Min Act: -0.1700
Data Index: 8610612 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.7968. Min Act: -0.1700
Data Index: 4612066 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9687. Min Range: -3.9687
Max Act: 3.7811. Min Act: -0.1700
Data Index: 3631348 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19