Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1569 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5865. Min Range: -3.5865
Max Act: 3.5865. Min Act: -0.1700
Data Index: 6690120 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5865. Min Range: -3.5865
Max Act: 3.5396. Min Act: -0.1700
Data Index: 4913411 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5865. Min Range: -3.5865
Max Act: 3.4769. Min Act: -0.1700
Data Index: 575550 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5865. Min Range: -3.5865
Max Act: 3.4456. Min Act: -0.1700
Data Index: 6022715 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5865. Min Range: -3.5865
Max Act: 3.4299. Min Act: -0.1700
Data Index: 8052245 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5865. Min Range: -3.5865
Max Act: 3.4299. Min Act: -0.1700
Data Index: 6971233 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5865. Min Range: -3.5865
Max Act: 3.4299. Min Act: -0.1700
Data Index: 4025737 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5865. Min Range: -3.5865
Max Act: 3.4299. Min Act: -0.1700
Data Index: 8565269 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5865. Min Range: -3.5865
Max Act: 3.3829. Min Act: -0.1700
Data Index: 6589201 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5865. Min Range: -3.5865
Max Act: 3.4299. Min Act: -0.1700
Data Index: 5184208 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5865. Min Range: -3.5865
Max Act: 3.3672. Min Act: -0.1700
Data Index: 1553602 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5865. Min Range: -3.5865
Max Act: 3.3672. Min Act: -0.1700
Data Index: 6702334 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5865. Min Range: -3.5865
Max Act: 3.3515. Min Act: -0.1700
Data Index: 1044022 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5865. Min Range: -3.5865
Max Act: 3.3829. Min Act: -0.1700
Data Index: 3176309 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5865. Min Range: -3.5865
Max Act: 3.3201. Min Act: -0.1700
Data Index: 5146375 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5865. Min Range: -3.5865
Max Act: 3.3358. Min Act: -0.1700
Data Index: 786171 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5865. Min Range: -3.5865
Max Act: 3.3358. Min Act: -0.1700
Data Index: 8803413 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5865. Min Range: -3.5865
Max Act: 3.3201. Min Act: -0.1700
Data Index: 4133384 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5865. Min Range: -3.5865
Max Act: 3.3201. Min Act: -0.1700
Data Index: 6594459 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5865. Min Range: -3.5865
Max Act: 3.3044. Min Act: -0.1700
Data Index: 7648761 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19