Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 408 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.6956. Min Range: -4.6956
Max Act: 4.6956. Min Act: -0.1700
Data Index: 8738749 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6956. Min Range: -4.6956
Max Act: 4.6331. Min Act: -0.1700
Data Index: 1987878 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6956. Min Range: -4.6956
Max Act: 4.6644. Min Act: -0.1700
Data Index: 1813302 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6956. Min Range: -4.6956
Max Act: 4.4144. Min Act: -0.1700
Data Index: 187209 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6956. Min Range: -4.6956
Max Act: 4.3519. Min Act: -0.1700
Data Index: 3342138 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6956. Min Range: -4.6956
Max Act: 4.3519. Min Act: -0.1700
Data Index: 7244667 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6956. Min Range: -4.6956
Max Act: 4.3519. Min Act: -0.1700
Data Index: 968821 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6956. Min Range: -4.6956
Max Act: 4.3206. Min Act: -0.1700
Data Index: 2638094 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6956. Min Range: -4.6956
Max Act: 4.2894. Min Act: -0.1700
Data Index: 1218897 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6956. Min Range: -4.6956
Max Act: 4.2894. Min Act: -0.1700
Data Index: 6646051 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6956. Min Range: -4.6956
Max Act: 4.3206. Min Act: -0.1700
Data Index: 5708905 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6956. Min Range: -4.6956
Max Act: 4.2581. Min Act: -0.1700
Data Index: 7630058 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6956. Min Range: -4.6956
Max Act: 4.2894. Min Act: -0.1700
Data Index: 1267924 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6956. Min Range: -4.6956
Max Act: 4.2894. Min Act: -0.1700
Data Index: 2197722 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6956. Min Range: -4.6956
Max Act: 4.2581. Min Act: -0.1700
Data Index: 2364558 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6956. Min Range: -4.6956
Max Act: 4.2581. Min Act: -0.1700
Data Index: 3835858 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6956. Min Range: -4.6956
Max Act: 4.2269. Min Act: -0.1700
Data Index: 6122612 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6956. Min Range: -4.6956
Max Act: 4.2581. Min Act: -0.1700
Data Index: 4145632 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6956. Min Range: -4.6956
Max Act: 4.2581. Min Act: -0.1700
Data Index: 4393110 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6956. Min Range: -4.6956
Max Act: 4.2581. Min Act: -0.1700
Data Index: 160258 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19