Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4031 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4224. Min Range: -3.4224
Max Act: 3.4224. Min Act: -0.1700
Data Index: 2000071 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4224. Min Range: -3.4224
Max Act: 3.4067. Min Act: -0.1700
Data Index: 1792855 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4224. Min Range: -3.4224
Max Act: 3.3754. Min Act: -0.1700
Data Index: 2630897 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4224. Min Range: -3.4224
Max Act: 3.3597. Min Act: -0.1700
Data Index: 1839721 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4224. Min Range: -3.4224
Max Act: 3.2812. Min Act: -0.1700
Data Index: 4869324 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4224. Min Range: -3.4224
Max Act: 3.3283. Min Act: -0.1700
Data Index: 6936420 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4224. Min Range: -3.4224
Max Act: 3.3126. Min Act: -0.1700
Data Index: 3530517 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4224. Min Range: -3.4224
Max Act: 3.2812. Min Act: -0.1700
Data Index: 8370272 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4224. Min Range: -3.4224
Max Act: 3.2655. Min Act: -0.1700
Data Index: 1198368 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4224. Min Range: -3.4224
Max Act: 3.2498. Min Act: -0.1700
Data Index: 161589 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4224. Min Range: -3.4224
Max Act: 3.2498. Min Act: -0.1700
Data Index: 5428501 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4224. Min Range: -3.4224
Max Act: 3.1082. Min Act: -0.1700
Data Index: 6244180 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4224. Min Range: -3.4224
Max Act: 3.1869. Min Act: -0.1700
Data Index: 6013221 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4224. Min Range: -3.4224
Max Act: 3.2183. Min Act: -0.1700
Data Index: 1119212 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4224. Min Range: -3.4224
Max Act: 3.2183. Min Act: -0.1700
Data Index: 2758947 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4224. Min Range: -3.4224
Max Act: 3.2183. Min Act: -0.1700
Data Index: 686324 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4224. Min Range: -3.4224
Max Act: 3.2183. Min Act: -0.1700
Data Index: 1887717 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4224. Min Range: -3.4224
Max Act: 3.2026. Min Act: -0.1700
Data Index: 1713106 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4224. Min Range: -3.4224
Max Act: 3.2812. Min Act: -0.1700
Data Index: 2188506 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4224. Min Range: -3.4224
Max Act: 3.2026. Min Act: -0.1700
Data Index: 5120031 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19