Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2110 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6617. Min Range: -7.6617
Max Act: 7.6617. Min Act: -0.1700
Data Index: 4931264 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6617. Min Range: -7.6617
Max Act: 7.6617. Min Act: -0.1700
Data Index: 3039140 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6617. Min Range: -7.6617
Max Act: 7.4429. Min Act: -0.1700
Data Index: 1581786 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6617. Min Range: -7.6617
Max Act: 7.3179. Min Act: -0.1700
Data Index: 6788208 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6617. Min Range: -7.6617
Max Act: 7.2867. Min Act: -0.1700
Data Index: 967845 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6617. Min Range: -7.6617
Max Act: 7.2242. Min Act: -0.1700
Data Index: 7099424 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6617. Min Range: -7.6617
Max Act: 7.2242. Min Act: -0.1700
Data Index: 539176 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6617. Min Range: -7.6617
Max Act: 7.1304. Min Act: -0.1700
Data Index: 8774813 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6617. Min Range: -7.6617
Max Act: 7.1304. Min Act: -0.1700
Data Index: 8780889 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6617. Min Range: -7.6617
Max Act: 7.1304. Min Act: -0.1700
Data Index: 1883404 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6617. Min Range: -7.6617
Max Act: 7.1304. Min Act: -0.1700
Data Index: 8050422 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6617. Min Range: -7.6617
Max Act: 7.0679. Min Act: -0.1700
Data Index: 564908 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6617. Min Range: -7.6617
Max Act: 7.0992. Min Act: -0.1700
Data Index: 7940430 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6617. Min Range: -7.6617
Max Act: 7.0679. Min Act: -0.1700
Data Index: 8170223 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6617. Min Range: -7.6617
Max Act: 7.0679. Min Act: -0.1700
Data Index: 4086414 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6617. Min Range: -7.6617
Max Act: 7.0367. Min Act: -0.1700
Data Index: 8698525 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6617. Min Range: -7.6617
Max Act: 7.0367. Min Act: -0.1700
Data Index: 5349112 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6617. Min Range: -7.6617
Max Act: 7.0367. Min Act: -0.1700
Data Index: 6389610 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6617. Min Range: -7.6617
Max Act: 7.0679. Min Act: -0.1700
Data Index: 473259 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6617. Min Range: -7.6617
Max Act: 7.0054. Min Act: -0.1700
Data Index: 5952279 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19