Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2173 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.4713. Min Range: -1.4713
Max Act: 1.4713. Min Act: -0.1700
Data Index: 1803491 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4713. Min Range: -1.4713
Max Act: 1.4185. Min Act: -0.1700
Data Index: 1953725 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4713. Min Range: -1.4713
Max Act: 1.4097. Min Act: -0.1700
Data Index: 660829 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4713. Min Range: -1.4713
Max Act: 1.4097. Min Act: -0.1700
Data Index: 8319346 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4713. Min Range: -1.4713
Max Act: 1.4008. Min Act: -0.1699
Data Index: 8643325 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4713. Min Range: -1.4713
Max Act: 1.3920. Min Act: -0.1700
Data Index: 3996900 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4713. Min Range: -1.4713
Max Act: 1.4097. Min Act: -0.1700
Data Index: 3569366 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4713. Min Range: -1.4713
Max Act: 1.4008. Min Act: -0.1699
Data Index: 3865533 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4713. Min Range: -1.4713
Max Act: 1.3920. Min Act: -0.1700
Data Index: 1415006 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4713. Min Range: -1.4713
Max Act: 1.3920. Min Act: -0.1700
Data Index: 4140492 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4713. Min Range: -1.4713
Max Act: 1.3832. Min Act: -0.1699
Data Index: 2570447 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4713. Min Range: -1.4713
Max Act: 1.3832. Min Act: -0.1696
Data Index: 5340312 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4713. Min Range: -1.4713
Max Act: 1.3832. Min Act: -0.1700
Data Index: 845174 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4713. Min Range: -1.4713
Max Act: 1.3744. Min Act: -0.1700
Data Index: 3599292 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4713. Min Range: -1.4713
Max Act: 1.3656. Min Act: -0.1700
Data Index: 3808753 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4713. Min Range: -1.4713
Max Act: 1.3656. Min Act: -0.1700
Data Index: 594311 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4713. Min Range: -1.4713
Max Act: 1.3656. Min Act: -0.1700
Data Index: 2813279 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4713. Min Range: -1.4713
Max Act: 1.3656. Min Act: -0.1700
Data Index: 1177912 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4713. Min Range: -1.4713
Max Act: 1.3656. Min Act: -0.1697
Data Index: 6558312 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4713. Min Range: -1.4713
Max Act: 1.3656. Min Act: -0.1700
Data Index: 2002133 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19