Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2933 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6522. Min Range: -5.6522
Max Act: 5.6522. Min Act: -0.1700
Data Index: 8148192 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6522. Min Range: -5.6522
Max Act: 5.4647. Min Act: -0.1700
Data Index: 2651444 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6522. Min Range: -5.6522
Max Act: 5.4335. Min Act: -0.1700
Data Index: 5560726 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6522. Min Range: -5.6522
Max Act: 5.4022. Min Act: -0.1700
Data Index: 451795 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6522. Min Range: -5.6522
Max Act: 5.4022. Min Act: -0.1700
Data Index: 3541330 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6522. Min Range: -5.6522
Max Act: 5.3710. Min Act: -0.1700
Data Index: 389948 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6522. Min Range: -5.6522
Max Act: 5.3397. Min Act: -0.1700
Data Index: 5402410 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6522. Min Range: -5.6522
Max Act: 5.3397. Min Act: -0.1700
Data Index: 5116606 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6522. Min Range: -5.6522
Max Act: 5.3397. Min Act: -0.1700
Data Index: 588937 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6522. Min Range: -5.6522
Max Act: 5.3085. Min Act: -0.1700
Data Index: 5988855 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6522. Min Range: -5.6522
Max Act: 5.3085. Min Act: -0.1700
Data Index: 5777612 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6522. Min Range: -5.6522
Max Act: 5.3085. Min Act: -0.1700
Data Index: 6857188 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6522. Min Range: -5.6522
Max Act: 5.2772. Min Act: -0.1700
Data Index: 4531377 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6522. Min Range: -5.6522
Max Act: 5.2772. Min Act: -0.1700
Data Index: 7270300 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6522. Min Range: -5.6522
Max Act: 5.2460. Min Act: -0.1700
Data Index: 7520640 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6522. Min Range: -5.6522
Max Act: 5.2772. Min Act: -0.1700
Data Index: 3823407 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6522. Min Range: -5.6522
Max Act: 5.2772. Min Act: -0.1700
Data Index: 8172108 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6522. Min Range: -5.6522
Max Act: 5.2460. Min Act: -0.1700
Data Index: 5072916 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6522. Min Range: -5.6522
Max Act: 5.2460. Min Act: -0.1700
Data Index: 6837799 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6522. Min Range: -5.6522
Max Act: 5.2460. Min Act: -0.1700
Data Index: 6903278 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19