Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1022 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3255. Min Range: -4.3255
Max Act: 4.3255. Min Act: -0.1700
Data Index: 8654268 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3255. Min Range: -4.3255
Max Act: 4.2943. Min Act: -0.1700
Data Index: 432866 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3255. Min Range: -4.3255
Max Act: 4.1693. Min Act: -0.1700
Data Index: 3749581 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3255. Min Range: -4.3255
Max Act: 4.1693. Min Act: -0.1700
Data Index: 5998570 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3255. Min Range: -4.3255
Max Act: 4.0130. Min Act: -0.1700
Data Index: 7709286 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3255. Min Range: -4.3255
Max Act: 4.0130. Min Act: -0.1700
Data Index: 2907268 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3255. Min Range: -4.3255
Max Act: 3.9504. Min Act: -0.1700
Data Index: 1615870 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3255. Min Range: -4.3255
Max Act: 3.9504. Min Act: -0.1700
Data Index: 6851721 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3255. Min Range: -4.3255
Max Act: 3.8879. Min Act: -0.1700
Data Index: 6626948 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3255. Min Range: -4.3255
Max Act: 3.8879. Min Act: -0.1700
Data Index: 8219021 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3255. Min Range: -4.3255
Max Act: 3.8879. Min Act: -0.1700
Data Index: 8573298 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3255. Min Range: -4.3255
Max Act: 3.8879. Min Act: -0.1700
Data Index: 300415 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3255. Min Range: -4.3255
Max Act: 3.8879. Min Act: -0.1700
Data Index: 215051 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3255. Min Range: -4.3255
Max Act: 3.8879. Min Act: -0.1700
Data Index: 8179767 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3255. Min Range: -4.3255
Max Act: 3.8254. Min Act: -0.1700
Data Index: 5009314 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3255. Min Range: -4.3255
Max Act: 3.8566. Min Act: -0.1700
Data Index: 7844318 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3255. Min Range: -4.3255
Max Act: 3.8566. Min Act: -0.1700
Data Index: 321195 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3255. Min Range: -4.3255
Max Act: 3.8879. Min Act: -0.1700
Data Index: 1929298 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3255. Min Range: -4.3255
Max Act: 3.8254. Min Act: -0.1700
Data Index: 2745023 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3255. Min Range: -4.3255
Max Act: 3.8254. Min Act: -0.1700
Data Index: 3741758 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19