Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3509 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.3542. Min Range: -1.3542
Max Act: 1.3542. Min Act: -0.1700
Data Index: 2551210 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3542. Min Range: -1.3542
Max Act: 1.3366. Min Act: -0.1700
Data Index: 2551185 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3542. Min Range: -1.3542
Max Act: 1.3013. Min Act: -0.1700
Data Index: 2551205 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3542. Min Range: -1.3542
Max Act: 1.2837. Min Act: -0.1699
Data Index: 2551217 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3542. Min Range: -1.3542
Max Act: 1.2660. Min Act: -0.1689
Data Index: 2551211 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3542. Min Range: -1.3542
Max Act: 1.2660. Min Act: -0.1700
Data Index: 2551203 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3542. Min Range: -1.3542
Max Act: 1.2484. Min Act: -0.1700
Data Index: 2551209 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3542. Min Range: -1.3542
Max Act: 1.2484. Min Act: -0.1693
Data Index: 2551193 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3542. Min Range: -1.3542
Max Act: 1.2308. Min Act: -0.1700
Data Index: 2551206 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3542. Min Range: -1.3542
Max Act: 1.1955. Min Act: -0.1700
Data Index: 2551194 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3542. Min Range: -1.3542
Max Act: 1.2132. Min Act: -0.1691
Data Index: 2551195 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3542. Min Range: -1.3542
Max Act: 1.2132. Min Act: -0.1700
Data Index: 2551197 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3542. Min Range: -1.3542
Max Act: 1.2132. Min Act: -0.1700
Data Index: 2551207 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3542. Min Range: -1.3542
Max Act: 1.1955. Min Act: -0.1700
Data Index: 2551213 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3542. Min Range: -1.3542
Max Act: 1.1779. Min Act: -0.1700
Data Index: 3588722 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3542. Min Range: -1.3542
Max Act: 1.1428. Min Act: -0.1700
Data Index: 1239088 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3542. Min Range: -1.3542
Max Act: 1.1252. Min Act: -0.1700
Data Index: 2551188 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3542. Min Range: -1.3542
Max Act: 1.1428. Min Act: -0.1700
Data Index: 2551214 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3542. Min Range: -1.3542
Max Act: 1.1252. Min Act: -0.1681
Data Index: 2551191 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3542. Min Range: -1.3542
Max Act: 1.1252. Min Act: -0.1700
Data Index: 2551201 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19