Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3289 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6565. Min Range: -5.6565
Max Act: 5.6565. Min Act: -0.1700
Data Index: 2549424 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6565. Min Range: -5.6565
Max Act: 5.5315. Min Act: -0.1700
Data Index: 1985995 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6565. Min Range: -5.6565
Max Act: 5.5315. Min Act: -0.1700
Data Index: 473604 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6565. Min Range: -5.6565
Max Act: 5.5315. Min Act: -0.1700
Data Index: 2395708 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6565. Min Range: -5.6565
Max Act: 5.5002. Min Act: -0.1700
Data Index: 2177487 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6565. Min Range: -5.6565
Max Act: 5.5315. Min Act: -0.1700
Data Index: 7179059 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6565. Min Range: -5.6565
Max Act: 5.4690. Min Act: -0.1700
Data Index: 3569675 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6565. Min Range: -5.6565
Max Act: 5.4690. Min Act: -0.1700
Data Index: 145790 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6565. Min Range: -5.6565
Max Act: 5.4690. Min Act: -0.1700
Data Index: 7622906 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6565. Min Range: -5.6565
Max Act: 5.4690. Min Act: -0.1700
Data Index: 4324405 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6565. Min Range: -5.6565
Max Act: 5.4690. Min Act: -0.1700
Data Index: 60288 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6565. Min Range: -5.6565
Max Act: 5.5002. Min Act: -0.1700
Data Index: 6456130 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6565. Min Range: -5.6565
Max Act: 5.4690. Min Act: -0.1700
Data Index: 5638576 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6565. Min Range: -5.6565
Max Act: 5.4690. Min Act: -0.1700
Data Index: 4960851 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6565. Min Range: -5.6565
Max Act: 5.4377. Min Act: -0.1700
Data Index: 3200487 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6565. Min Range: -5.6565
Max Act: 5.4377. Min Act: -0.1700
Data Index: 3134457 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6565. Min Range: -5.6565
Max Act: 5.4377. Min Act: -0.1700
Data Index: 6682550 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6565. Min Range: -5.6565
Max Act: 5.4065. Min Act: -0.1700
Data Index: 6885996 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6565. Min Range: -5.6565
Max Act: 5.4377. Min Act: -0.1700
Data Index: 749554 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6565. Min Range: -5.6565
Max Act: 5.4377. Min Act: -0.1700
Data Index: 2930618 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19