Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4351 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4763. Min Range: -4.4763
Max Act: 4.4763. Min Act: -0.1700
Data Index: 5435129 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4763. Min Range: -4.4763
Max Act: 4.4451. Min Act: -0.1700
Data Index: 8236885 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4763. Min Range: -4.4763
Max Act: 4.4451. Min Act: -0.1700
Data Index: 7772138 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4763. Min Range: -4.4763
Max Act: 4.4138. Min Act: -0.1700
Data Index: 505921 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4763. Min Range: -4.4763
Max Act: 4.4451. Min Act: -0.1700
Data Index: 2945051 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4763. Min Range: -4.4763
Max Act: 4.3513. Min Act: -0.1700
Data Index: 7728637 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4763. Min Range: -4.4763
Max Act: 4.3201. Min Act: -0.1700
Data Index: 2138948 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4763. Min Range: -4.4763
Max Act: 4.3201. Min Act: -0.1700
Data Index: 4538922 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4763. Min Range: -4.4763
Max Act: 4.3513. Min Act: -0.1700
Data Index: 7428950 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4763. Min Range: -4.4763
Max Act: 4.2576. Min Act: -0.1700
Data Index: 7633614 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4763. Min Range: -4.4763
Max Act: 4.2888. Min Act: -0.1700
Data Index: 155206 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4763. Min Range: -4.4763
Max Act: 4.2888. Min Act: -0.1700
Data Index: 6833154 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4763. Min Range: -4.4763
Max Act: 4.2888. Min Act: -0.1700
Data Index: 2740674 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4763. Min Range: -4.4763
Max Act: 4.2576. Min Act: -0.1700
Data Index: 1435093 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4763. Min Range: -4.4763
Max Act: 4.2263. Min Act: -0.1700
Data Index: 3063686 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4763. Min Range: -4.4763
Max Act: 4.2576. Min Act: -0.1700
Data Index: 3317676 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4763. Min Range: -4.4763
Max Act: 4.2263. Min Act: -0.1700
Data Index: 2200177 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4763. Min Range: -4.4763
Max Act: 4.1951. Min Act: -0.1700
Data Index: 4066969 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4763. Min Range: -4.4763
Max Act: 4.2263. Min Act: -0.1700
Data Index: 4120365 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4763. Min Range: -4.4763
Max Act: 4.2263. Min Act: -0.1700
Data Index: 466475 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19