Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3997 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.7287. Min Act: -0.1700
Data Index: 7460029 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.6662. Min Act: -0.1700
Data Index: 1885875 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.6662. Min Act: -0.1700
Data Index: 1502456 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.6037. Min Act: -0.1700
Data Index: 3567771 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.6037. Min Act: -0.1700
Data Index: 7603335 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.5724. Min Act: -0.1700
Data Index: 2565227 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.5099. Min Act: -0.1700
Data Index: 7771210 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.4787. Min Act: -0.1700
Data Index: 960728 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.4787. Min Act: -0.1700
Data Index: 1051646 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.5099. Min Act: -0.1700
Data Index: 8152570 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.4162. Min Act: -0.1700
Data Index: 5113457 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.4787. Min Act: -0.1700
Data Index: 8720009 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.3849. Min Act: -0.1700
Data Index: 2368740 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.3849. Min Act: -0.1700
Data Index: 3919315 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.3849. Min Act: -0.1700
Data Index: 4203576 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.3849. Min Act: -0.1700
Data Index: 6957048 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.3849. Min Act: -0.1700
Data Index: 3799044 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.3224. Min Act: -0.1700
Data Index: 3532291 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.3537. Min Act: -0.1700
Data Index: 3314022 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7287. Min Range: -5.7287
Max Act: 5.3224. Min Act: -0.1700
Data Index: 3041628 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19