Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2501 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5965. Min Range: -3.5965
Max Act: 3.5965. Min Act: -0.1700
Data Index: 8661409 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5965. Min Range: -3.5965
Max Act: 3.5652. Min Act: -0.1700
Data Index: 6701275 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5965. Min Range: -3.5965
Max Act: 3.5339. Min Act: -0.1700
Data Index: 5988183 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5965. Min Range: -3.5965
Max Act: 3.5026. Min Act: -0.1700
Data Index: 8182824 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5965. Min Range: -3.5965
Max Act: 3.5026. Min Act: -0.1700
Data Index: 6036288 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5965. Min Range: -3.5965
Max Act: 3.5026. Min Act: -0.1700
Data Index: 1203799 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5965. Min Range: -3.5965
Max Act: 3.4713. Min Act: -0.1700
Data Index: 237127 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5965. Min Range: -3.5965
Max Act: 3.4556. Min Act: -0.1700
Data Index: 5460044 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5965. Min Range: -3.5965
Max Act: 3.4556. Min Act: -0.1700
Data Index: 7809629 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5965. Min Range: -3.5965
Max Act: 3.4399. Min Act: -0.1700
Data Index: 5538694 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5965. Min Range: -3.5965
Max Act: 3.4086. Min Act: -0.1700
Data Index: 237119 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5965. Min Range: -3.5965
Max Act: 3.4243. Min Act: -0.1700
Data Index: 2017234 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5965. Min Range: -3.5965
Max Act: 3.4243. Min Act: -0.1700
Data Index: 7348253 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5965. Min Range: -3.5965
Max Act: 3.4086. Min Act: -0.1700
Data Index: 7433151 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5965. Min Range: -3.5965
Max Act: 3.4086. Min Act: -0.1700
Data Index: 1194425 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5965. Min Range: -3.5965
Max Act: 3.4086. Min Act: -0.1700
Data Index: 3371600 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5965. Min Range: -3.5965
Max Act: 3.4086. Min Act: -0.1700
Data Index: 2355187 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5965. Min Range: -3.5965
Max Act: 3.4086. Min Act: -0.1700
Data Index: 65335 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5965. Min Range: -3.5965
Max Act: 3.3929. Min Act: -0.1700
Data Index: 3403763 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5965. Min Range: -3.5965
Max Act: 3.3615. Min Act: -0.1700
Data Index: 5190670 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19