Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1781 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0714. Min Range: -5.0714
Max Act: 5.0402. Min Act: -0.1700
Data Index: 4395500 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0714. Min Range: -5.0714
Max Act: 5.0714. Min Act: -0.1700
Data Index: 6076369 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0714. Min Range: -5.0714
Max Act: 5.0089. Min Act: -0.1700
Data Index: 833634 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0714. Min Range: -5.0714
Max Act: 5.0089. Min Act: -0.1700
Data Index: 410257 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0714. Min Range: -5.0714
Max Act: 4.9777. Min Act: -0.1700
Data Index: 8163859 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0714. Min Range: -5.0714
Max Act: 5.0089. Min Act: -0.1700
Data Index: 5648610 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0714. Min Range: -5.0714
Max Act: 5.0089. Min Act: -0.1700
Data Index: 7762833 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0714. Min Range: -5.0714
Max Act: 4.9777. Min Act: -0.1700
Data Index: 4715536 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0714. Min Range: -5.0714
Max Act: 4.9464. Min Act: -0.1700
Data Index: 8216072 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0714. Min Range: -5.0714
Max Act: 4.9777. Min Act: -0.1700
Data Index: 7321859 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0714. Min Range: -5.0714
Max Act: 4.9777. Min Act: -0.1700
Data Index: 8387214 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0714. Min Range: -5.0714
Max Act: 4.9464. Min Act: -0.1700
Data Index: 7934109 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0714. Min Range: -5.0714
Max Act: 4.9464. Min Act: -0.1700
Data Index: 8081528 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0714. Min Range: -5.0714
Max Act: 4.9464. Min Act: -0.1700
Data Index: 7490317 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0714. Min Range: -5.0714
Max Act: 4.9464. Min Act: -0.1700
Data Index: 8216073 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0714. Min Range: -5.0714
Max Act: 4.9464. Min Act: -0.1700
Data Index: 7013983 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0714. Min Range: -5.0714
Max Act: 4.9152. Min Act: -0.1700
Data Index: 3755756 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0714. Min Range: -5.0714
Max Act: 4.9152. Min Act: -0.1700
Data Index: 2253035 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0714. Min Range: -5.0714
Max Act: 4.9464. Min Act: -0.1700
Data Index: 6115766 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0714. Min Range: -5.0714
Max Act: 4.9464. Min Act: -0.1700
Data Index: 4072606 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19