Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3709 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.0221. Min Range: -1.0221
Max Act: 1.0221. Min Act: -0.1700
Data Index: 381849 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0221. Min Range: -1.0221
Max Act: 1.0047. Min Act: -0.1700
Data Index: 2549848 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0221. Min Range: -1.0221
Max Act: 1.0047. Min Act: -0.1700
Data Index: 2719067 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0221. Min Range: -1.0221
Max Act: 1.0047. Min Act: -0.1700
Data Index: 5535968 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0221. Min Range: -1.0221
Max Act: 0.9960. Min Act: -0.1700
Data Index: 5450745 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0221. Min Range: -1.0221
Max Act: 1.0047. Min Act: -0.1700
Data Index: 8257699 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0221. Min Range: -1.0221
Max Act: 0.9960. Min Act: -0.1700
Data Index: 7410432 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0221. Min Range: -1.0221
Max Act: 0.9873. Min Act: -0.1700
Data Index: 25309 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0221. Min Range: -1.0221
Max Act: 0.9873. Min Act: -0.1700
Data Index: 780434 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0221. Min Range: -1.0221
Max Act: 0.9873. Min Act: -0.1700
Data Index: 6081394 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0221. Min Range: -1.0221
Max Act: 0.9700. Min Act: -0.1700
Data Index: 4165063 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0221. Min Range: -1.0221
Max Act: 0.9873. Min Act: -0.1699
Data Index: 5308230 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0221. Min Range: -1.0221
Max Act: 0.9787. Min Act: -0.1700
Data Index: 7717158 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0221. Min Range: -1.0221
Max Act: 0.9787. Min Act: -0.1700
Data Index: 6530499 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0221. Min Range: -1.0221
Max Act: 0.9787. Min Act: -0.1700
Data Index: 3107550 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0221. Min Range: -1.0221
Max Act: 0.9787. Min Act: -0.1700
Data Index: 541143 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0221. Min Range: -1.0221
Max Act: 0.9787. Min Act: -0.1700
Data Index: 3079323 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0221. Min Range: -1.0221
Max Act: 0.9700. Min Act: -0.1700
Data Index: 1695276 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0221. Min Range: -1.0221
Max Act: 0.9614. Min Act: -0.1700
Data Index: 2042028 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0221. Min Range: -1.0221
Max Act: 0.9700. Min Act: -0.1700
Data Index: 2143613 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19