Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1375 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1450. Min Range: -6.1450
Max Act: 6.1450. Min Act: -0.1700
Data Index: 1780466 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1450. Min Range: -6.1450
Max Act: 6.0513. Min Act: -0.1700
Data Index: 430649 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1450. Min Range: -6.1450
Max Act: 5.9575. Min Act: -0.1700
Data Index: 1080189 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1450. Min Range: -6.1450
Max Act: 5.9888. Min Act: -0.1700
Data Index: 5856582 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1450. Min Range: -6.1450
Max Act: 5.9888. Min Act: -0.1700
Data Index: 6118571 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1450. Min Range: -6.1450
Max Act: 5.9575. Min Act: -0.1700
Data Index: 7805637 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1450. Min Range: -6.1450
Max Act: 5.9575. Min Act: -0.1700
Data Index: 3661413 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1450. Min Range: -6.1450
Max Act: 5.9575. Min Act: -0.1700
Data Index: 6217807 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1450. Min Range: -6.1450
Max Act: 5.9888. Min Act: -0.1700
Data Index: 5939932 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1450. Min Range: -6.1450
Max Act: 5.9575. Min Act: -0.1700
Data Index: 1767131 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1450. Min Range: -6.1450
Max Act: 5.9263. Min Act: -0.1700
Data Index: 325572 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1450. Min Range: -6.1450
Max Act: 5.9263. Min Act: -0.1700
Data Index: 1440504 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1450. Min Range: -6.1450
Max Act: 5.9575. Min Act: -0.1700
Data Index: 6756777 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1450. Min Range: -6.1450
Max Act: 5.9575. Min Act: -0.1700
Data Index: 4055197 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1450. Min Range: -6.1450
Max Act: 5.9263. Min Act: -0.1700
Data Index: 5870133 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1450. Min Range: -6.1450
Max Act: 5.9263. Min Act: -0.1700
Data Index: 5513097 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1450. Min Range: -6.1450
Max Act: 5.9263. Min Act: -0.1700
Data Index: 3102850 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1450. Min Range: -6.1450
Max Act: 5.9263. Min Act: -0.1700
Data Index: 2344229 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1450. Min Range: -6.1450
Max Act: 5.8950. Min Act: -0.1700
Data Index: 4946081 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1450. Min Range: -6.1450
Max Act: 5.9263. Min Act: -0.1700
Data Index: 5269359 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19