Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 793 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.1206. Min Range: -9.1206
Max Act: 9.1206. Min Act: -0.1700
Data Index: 1794750 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1206. Min Range: -9.1206
Max Act: 8.9956. Min Act: -0.1700
Data Index: 7769960 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1206. Min Range: -9.1206
Max Act: 8.9956. Min Act: -0.1700
Data Index: 3722212 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1206. Min Range: -9.1206
Max Act: 8.8706. Min Act: -0.1700
Data Index: 4747889 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1206. Min Range: -9.1206
Max Act: 8.7456. Min Act: -0.1700
Data Index: 2861030 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1206. Min Range: -9.1206
Max Act: 8.7456. Min Act: -0.1700
Data Index: 5119726 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1206. Min Range: -9.1206
Max Act: 8.7456. Min Act: -0.1700
Data Index: 5157405 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1206. Min Range: -9.1206
Max Act: 8.7456. Min Act: -0.1700
Data Index: 4747891 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1206. Min Range: -9.1206
Max Act: 8.6831. Min Act: -0.1700
Data Index: 4365994 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1206. Min Range: -9.1206
Max Act: 8.6831. Min Act: -0.1700
Data Index: 8016267 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1206. Min Range: -9.1206
Max Act: 8.6831. Min Act: -0.1700
Data Index: 3722211 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1206. Min Range: -9.1206
Max Act: 8.6206. Min Act: -0.1700
Data Index: 8240194 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1206. Min Range: -9.1206
Max Act: 8.5581. Min Act: -0.1700
Data Index: 5512989 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1206. Min Range: -9.1206
Max Act: 8.6831. Min Act: -0.1700
Data Index: 248967 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1206. Min Range: -9.1206
Max Act: 8.5581. Min Act: -0.1700
Data Index: 1071251 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1206. Min Range: -9.1206
Max Act: 8.5581. Min Act: -0.1700
Data Index: 7567567 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1206. Min Range: -9.1206
Max Act: 8.4331. Min Act: -0.1700
Data Index: 4037867 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1206. Min Range: -9.1206
Max Act: 8.4956. Min Act: -0.1700
Data Index: 8617003 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1206. Min Range: -9.1206
Max Act: 8.4956. Min Act: -0.1700
Data Index: 5381333 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1206. Min Range: -9.1206
Max Act: 8.4331. Min Act: -0.1700
Data Index: 7969629 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19