Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3125 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6961. Min Range: -9.6961
Max Act: 9.6961. Min Act: -0.1700
Data Index: 10323 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6961. Min Range: -9.6961
Max Act: 9.6961. Min Act: -0.1700
Data Index: 4886938 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6961. Min Range: -9.6961
Max Act: 9.6336. Min Act: -0.1700
Data Index: 1647057 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6961. Min Range: -9.6961
Max Act: 9.4461. Min Act: -0.1700
Data Index: 3322744 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6961. Min Range: -9.6961
Max Act: 9.5086. Min Act: -0.1700
Data Index: 2038246 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6961. Min Range: -9.6961
Max Act: 9.4461. Min Act: -0.1700
Data Index: 4990417 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6961. Min Range: -9.6961
Max Act: 9.5086. Min Act: -0.1700
Data Index: 5767182 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6961. Min Range: -9.6961
Max Act: 9.4461. Min Act: -0.1700
Data Index: 6831860 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6961. Min Range: -9.6961
Max Act: 9.4461. Min Act: -0.1700
Data Index: 3214267 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6961. Min Range: -9.6961
Max Act: 9.4461. Min Act: -0.1700
Data Index: 7108443 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6961. Min Range: -9.6961
Max Act: 9.4461. Min Act: -0.1700
Data Index: 6347346 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6961. Min Range: -9.6961
Max Act: 9.4461. Min Act: -0.1700
Data Index: 8753162 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6961. Min Range: -9.6961
Max Act: 9.3836. Min Act: -0.1700
Data Index: 3471787 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6961. Min Range: -9.6961
Max Act: 9.3836. Min Act: -0.1700
Data Index: 7012827 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6961. Min Range: -9.6961
Max Act: 9.3836. Min Act: -0.1700
Data Index: 3224290 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6961. Min Range: -9.6961
Max Act: 9.3836. Min Act: -0.1700
Data Index: 5144203 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6961. Min Range: -9.6961
Max Act: 9.3211. Min Act: -0.1700
Data Index: 3040638 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6961. Min Range: -9.6961
Max Act: 9.3211. Min Act: -0.1700
Data Index: 167817 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6961. Min Range: -9.6961
Max Act: 9.3211. Min Act: -0.1700
Data Index: 5198151 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6961. Min Range: -9.6961
Max Act: 9.3211. Min Act: -0.1700
Data Index: 6826849 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19