Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3851 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5950. Min Range: -3.5950
Max Act: 3.5950. Min Act: -0.1700
Data Index: 6189139 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5950. Min Range: -3.5950
Max Act: 3.3600. Min Act: -0.1700
Data Index: 8096234 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5950. Min Range: -3.5950
Max Act: 3.3443. Min Act: -0.1700
Data Index: 1463895 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5950. Min Range: -3.5950
Max Act: 3.3129. Min Act: -0.1700
Data Index: 7776880 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5950. Min Range: -3.5950
Max Act: 3.3443. Min Act: -0.1700
Data Index: 3296410 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5950. Min Range: -3.5950
Max Act: 3.3286. Min Act: -0.1700
Data Index: 4100223 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5950. Min Range: -3.5950
Max Act: 3.3129. Min Act: -0.1700
Data Index: 4071549 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5950. Min Range: -3.5950
Max Act: 3.2972. Min Act: -0.1700
Data Index: 8659807 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5950. Min Range: -3.5950
Max Act: 3.2972. Min Act: -0.1700
Data Index: 4975031 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5950. Min Range: -3.5950
Max Act: 3.2815. Min Act: -0.1700
Data Index: 4328750 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5950. Min Range: -3.5950
Max Act: 3.2658. Min Act: -0.1700
Data Index: 1185939 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5950. Min Range: -3.5950
Max Act: 3.2658. Min Act: -0.1700
Data Index: 8031178 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5950. Min Range: -3.5950
Max Act: 3.2658. Min Act: -0.1700
Data Index: 7868993 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5950. Min Range: -3.5950
Max Act: 3.2501. Min Act: -0.1700
Data Index: 4543647 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5950. Min Range: -3.5950
Max Act: 3.2658. Min Act: -0.1700
Data Index: 3633112 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5950. Min Range: -3.5950
Max Act: 3.2187. Min Act: -0.1700
Data Index: 7489308 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5950. Min Range: -3.5950
Max Act: 3.2658. Min Act: -0.1700
Data Index: 5594706 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5950. Min Range: -3.5950
Max Act: 3.2658. Min Act: -0.1700
Data Index: 3157946 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5950. Min Range: -3.5950
Max Act: 3.2344. Min Act: -0.1700
Data Index: 8206256 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5950. Min Range: -3.5950
Max Act: 3.2344. Min Act: -0.1700
Data Index: 5918642 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19