Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3398 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.8573. Min Act: -0.1700
Data Index: 2579210 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.6697. Min Act: -0.1700
Data Index: 3139725 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.5914. Min Act: -0.1700
Data Index: 924191 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.5914. Min Act: -0.1700
Data Index: 7136054 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.5601. Min Act: -0.1700
Data Index: 4441238 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.5601. Min Act: -0.1700
Data Index: 2933035 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.5758. Min Act: -0.1700
Data Index: 4375696 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.5444. Min Act: -0.1700
Data Index: 2256879 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.5444. Min Act: -0.1700
Data Index: 6641101 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.5444. Min Act: -0.1700
Data Index: 27384 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.5601. Min Act: -0.1700
Data Index: 4815228 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.5288. Min Act: -0.1700
Data Index: 3275499 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.5288. Min Act: -0.1700
Data Index: 4762947 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.5288. Min Act: -0.1700
Data Index: 6694796 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.5131. Min Act: -0.1700
Data Index: 4103159 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.4975. Min Act: -0.1700
Data Index: 2726257 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.4975. Min Act: -0.1700
Data Index: 6267408 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.5131. Min Act: -0.1700
Data Index: 574978 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.4818. Min Act: -0.1700
Data Index: 2952731 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8573. Min Range: -3.8573
Max Act: 3.4818. Min Act: -0.1700
Data Index: 2541828 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19