Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 70 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9956. Min Range: -4.9956
Max Act: 4.9956. Min Act: -0.1700
Data Index: 2590222 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9956. Min Range: -4.9956
Max Act: 4.8081. Min Act: -0.1700
Data Index: 2738130 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9956. Min Range: -4.9956
Max Act: 4.7769. Min Act: -0.1700
Data Index: 2738131 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9956. Min Range: -4.9956
Max Act: 4.7456. Min Act: -0.1700
Data Index: 5394440 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9956. Min Range: -4.9956
Max Act: 4.7144. Min Act: -0.1700
Data Index: 4720181 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9956. Min Range: -4.9956
Max Act: 4.7144. Min Act: -0.1700
Data Index: 8474183 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9956. Min Range: -4.9956
Max Act: 4.6831. Min Act: -0.1700
Data Index: 5352102 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9956. Min Range: -4.9956
Max Act: 4.6831. Min Act: -0.1700
Data Index: 1848338 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9956. Min Range: -4.9956
Max Act: 4.6831. Min Act: -0.1700
Data Index: 6606582 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9956. Min Range: -4.9956
Max Act: 4.6519. Min Act: -0.1700
Data Index: 8272933 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9956. Min Range: -4.9956
Max Act: 4.6831. Min Act: -0.1700
Data Index: 7490615 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9956. Min Range: -4.9956
Max Act: 4.6831. Min Act: -0.1700
Data Index: 7427229 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9956. Min Range: -4.9956
Max Act: 4.6519. Min Act: -0.1700
Data Index: 8381293 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9956. Min Range: -4.9956
Max Act: 4.6519. Min Act: -0.1694
Data Index: 589785 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9956. Min Range: -4.9956
Max Act: 4.6519. Min Act: -0.1700
Data Index: 5541971 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9956. Min Range: -4.9956
Max Act: 4.6519. Min Act: -0.1700
Data Index: 2557578 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9956. Min Range: -4.9956
Max Act: 4.6206. Min Act: -0.1700
Data Index: 2557564 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9956. Min Range: -4.9956
Max Act: 4.6206. Min Act: -0.1700
Data Index: 924494 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9956. Min Range: -4.9956
Max Act: 4.6206. Min Act: -0.1700
Data Index: 5021829 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9956. Min Range: -4.9956
Max Act: 4.6206. Min Act: -0.1697
Data Index: 5206640 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19