Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5715 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5051. Min Range: -6.5051
Max Act: 6.5051. Min Act: -0.1700
Data Index: 8140124 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5051. Min Range: -6.5051
Max Act: 6.4426. Min Act: -0.1700
Data Index: 8268522 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5051. Min Range: -6.5051
Max Act: 6.4426. Min Act: -0.1700
Data Index: 7964053 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5051. Min Range: -6.5051
Max Act: 6.3489. Min Act: -0.1700
Data Index: 7654382 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5051. Min Range: -6.5051
Max Act: 6.3489. Min Act: -0.1700
Data Index: 206793 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5051. Min Range: -6.5051
Max Act: 6.3176. Min Act: -0.1700
Data Index: 7403837 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5051. Min Range: -6.5051
Max Act: 6.2239. Min Act: -0.1700
Data Index: 3647370 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5051. Min Range: -6.5051
Max Act: 6.1926. Min Act: -0.1700
Data Index: 2359371 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5051. Min Range: -6.5051
Max Act: 6.1926. Min Act: -0.1700
Data Index: 2772117 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5051. Min Range: -6.5051
Max Act: 6.1926. Min Act: -0.1700
Data Index: 8226545 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5051. Min Range: -6.5051
Max Act: 6.1926. Min Act: -0.1700
Data Index: 1259100 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5051. Min Range: -6.5051
Max Act: 6.1926. Min Act: -0.1700
Data Index: 1420556 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5051. Min Range: -6.5051
Max Act: 6.1926. Min Act: -0.1700
Data Index: 6426960 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5051. Min Range: -6.5051
Max Act: 6.1614. Min Act: -0.1700
Data Index: 4581430 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5051. Min Range: -6.5051
Max Act: 6.1614. Min Act: -0.1700
Data Index: 8575557 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5051. Min Range: -6.5051
Max Act: 6.1301. Min Act: -0.1700
Data Index: 8316648 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5051. Min Range: -6.5051
Max Act: 6.1301. Min Act: -0.1700
Data Index: 2761617 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5051. Min Range: -6.5051
Max Act: 6.1301. Min Act: -0.1700
Data Index: 5313016 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5051. Min Range: -6.5051
Max Act: 6.0989. Min Act: -0.1700
Data Index: 6580390 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5051. Min Range: -6.5051
Max Act: 6.0676. Min Act: -0.1700
Data Index: 5758940 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19