Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4612 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6489. Min Range: -4.6489
Max Act: 4.6489. Min Act: -0.1700
Data Index: 1251598 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6489. Min Range: -4.6489
Max Act: 4.6177. Min Act: -0.1700
Data Index: 937599 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6489. Min Range: -4.6489
Max Act: 4.5864. Min Act: -0.1700
Data Index: 1251597 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6489. Min Range: -4.6489
Max Act: 4.4614. Min Act: -0.1700
Data Index: 1251595 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6489. Min Range: -4.6489
Max Act: 4.4614. Min Act: -0.1700
Data Index: 758712 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6489. Min Range: -4.6489
Max Act: 4.4614. Min Act: -0.1700
Data Index: 4390846 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6489. Min Range: -4.6489
Max Act: 4.4614. Min Act: -0.1700
Data Index: 3020019 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6489. Min Range: -4.6489
Max Act: 4.4614. Min Act: -0.1700
Data Index: 474988 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6489. Min Range: -4.6489
Max Act: 4.4927. Min Act: -0.1700
Data Index: 153260 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6489. Min Range: -4.6489
Max Act: 4.3989. Min Act: -0.1700
Data Index: 1789800 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6489. Min Range: -4.6489
Max Act: 4.4302. Min Act: -0.1700
Data Index: 131416 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6489. Min Range: -4.6489
Max Act: 4.3989. Min Act: -0.1700
Data Index: 5756131 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6489. Min Range: -4.6489
Max Act: 4.3989. Min Act: -0.1700
Data Index: 6019069 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6489. Min Range: -4.6489
Max Act: 4.4302. Min Act: -0.1700
Data Index: 3677682 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6489. Min Range: -4.6489
Max Act: 4.3989. Min Act: -0.1700
Data Index: 6259978 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6489. Min Range: -4.6489
Max Act: 4.3989. Min Act: -0.1700
Data Index: 6192305 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6489. Min Range: -4.6489
Max Act: 4.3677. Min Act: -0.1700
Data Index: 8479894 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6489. Min Range: -4.6489
Max Act: 4.3989. Min Act: -0.1700
Data Index: 3909003 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6489. Min Range: -4.6489
Max Act: 4.3677. Min Act: -0.1700
Data Index: 38947 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6489. Min Range: -4.6489
Max Act: 4.3677. Min Act: -0.1700
Data Index: 6022950 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19