Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2086 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8215. Min Range: -2.8215
Max Act: 2.7897. Min Act: -0.1700
Data Index: 3712955 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8215. Min Range: -2.8215
Max Act: 2.8215. Min Act: -0.1700
Data Index: 5175720 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8215. Min Range: -2.8215
Max Act: 2.7099. Min Act: -0.1700
Data Index: 4241148 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8215. Min Range: -2.8215
Max Act: 2.6939. Min Act: -0.1700
Data Index: 3285211 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8215. Min Range: -2.8215
Max Act: 2.6939. Min Act: -0.1700
Data Index: 5188254 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8215. Min Range: -2.8215
Max Act: 2.6939. Min Act: -0.1700
Data Index: 244742 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8215. Min Range: -2.8215
Max Act: 2.6939. Min Act: -0.1700
Data Index: 8142283 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8215. Min Range: -2.8215
Max Act: 2.6618. Min Act: -0.1700
Data Index: 2561399 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8215. Min Range: -2.8215
Max Act: 2.6778. Min Act: -0.1700
Data Index: 4659304 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8215. Min Range: -2.8215
Max Act: 2.6778. Min Act: -0.1700
Data Index: 4978494 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8215. Min Range: -2.8215
Max Act: 2.6618. Min Act: -0.1700
Data Index: 2557803 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8215. Min Range: -2.8215
Max Act: 2.6618. Min Act: -0.1700
Data Index: 5953815 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8215. Min Range: -2.8215
Max Act: 2.6618. Min Act: -0.1700
Data Index: 1631433 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8215. Min Range: -2.8215
Max Act: 2.6458. Min Act: -0.1700
Data Index: 6694664 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8215. Min Range: -2.8215
Max Act: 2.6458. Min Act: -0.1700
Data Index: 4532615 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8215. Min Range: -2.8215
Max Act: 2.6297. Min Act: -0.1700
Data Index: 1015080 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8215. Min Range: -2.8215
Max Act: 2.6297. Min Act: -0.1700
Data Index: 1361142 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8215. Min Range: -2.8215
Max Act: 2.6297. Min Act: -0.1700
Data Index: 821839 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8215. Min Range: -2.8215
Max Act: 2.6297. Min Act: -0.1700
Data Index: 5929220 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8215. Min Range: -2.8215
Max Act: 2.6297. Min Act: -0.1700
Data Index: 2971772 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19