Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1988 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.8214. Min Range: -13.8214
Max Act: 13.8214. Min Act: -0.1700
Data Index: 7922482 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.8214. Min Range: -13.8214
Max Act: 13.7589. Min Act: -0.1700
Data Index: 6520449 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.8214. Min Range: -13.8214
Max Act: 13.6964. Min Act: -0.1700
Data Index: 6254365 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.8214. Min Range: -13.8214
Max Act: 13.4464. Min Act: -0.1700
Data Index: 5644171 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.8214. Min Range: -13.8214
Max Act: 13.4464. Min Act: -0.1700
Data Index: 8009328 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.8214. Min Range: -13.8214
Max Act: 13.3839. Min Act: -0.1700
Data Index: 7009186 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.8214. Min Range: -13.8214
Max Act: 13.3839. Min Act: -0.1700
Data Index: 5106208 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.8214. Min Range: -13.8214
Max Act: 13.3214. Min Act: -0.1700
Data Index: 4697747 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.8214. Min Range: -13.8214
Max Act: 13.3214. Min Act: -0.1700
Data Index: 2655193 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.8214. Min Range: -13.8214
Max Act: 13.3214. Min Act: -0.1700
Data Index: 6719057 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.8214. Min Range: -13.8214
Max Act: 13.2589. Min Act: -0.1700
Data Index: 8165563 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.8214. Min Range: -13.8214
Max Act: 13.2589. Min Act: -0.1700
Data Index: 728011 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.8214. Min Range: -13.8214
Max Act: 13.1964. Min Act: -0.1700
Data Index: 2362456 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.8214. Min Range: -13.8214
Max Act: 13.3214. Min Act: -0.1700
Data Index: 2509983 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.8214. Min Range: -13.8214
Max Act: 13.1964. Min Act: -0.1700
Data Index: 7133297 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.8214. Min Range: -13.8214
Max Act: 13.1964. Min Act: -0.1700
Data Index: 5775149 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.8214. Min Range: -13.8214
Max Act: 13.1339. Min Act: -0.1700
Data Index: 177928 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.8214. Min Range: -13.8214
Max Act: 13.1339. Min Act: -0.1700
Data Index: 221059 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.8214. Min Range: -13.8214
Max Act: 13.0714. Min Act: -0.1700
Data Index: 621308 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.8214. Min Range: -13.8214
Max Act: 13.0714. Min Act: -0.1700
Data Index: 4498036 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #19