Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6053 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8136. Min Range: -9.8136
Max Act: 9.8136. Min Act: -0.1700
Data Index: 8274518 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8136. Min Range: -9.8136
Max Act: 9.4386. Min Act: -0.1700
Data Index: 5496706 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8136. Min Range: -9.8136
Max Act: 9.4386. Min Act: -0.1700
Data Index: 3640100 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8136. Min Range: -9.8136
Max Act: 9.3761. Min Act: -0.1700
Data Index: 4857414 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8136. Min Range: -9.8136
Max Act: 9.3761. Min Act: -0.1700
Data Index: 1901259 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8136. Min Range: -9.8136
Max Act: 9.2511. Min Act: -0.1700
Data Index: 7975346 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8136. Min Range: -9.8136
Max Act: 9.0636. Min Act: -0.1700
Data Index: 8216403 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8136. Min Range: -9.8136
Max Act: 9.0011. Min Act: -0.1700
Data Index: 3862160 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8136. Min Range: -9.8136
Max Act: 9.0011. Min Act: -0.1700
Data Index: 7589981 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8136. Min Range: -9.8136
Max Act: 9.0011. Min Act: -0.1700
Data Index: 2539532 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8136. Min Range: -9.8136
Max Act: 9.0011. Min Act: -0.1700
Data Index: 8277038 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8136. Min Range: -9.8136
Max Act: 8.9386. Min Act: -0.1700
Data Index: 7217298 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8136. Min Range: -9.8136
Max Act: 8.9386. Min Act: -0.1700
Data Index: 8642046 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8136. Min Range: -9.8136
Max Act: 8.7511. Min Act: -0.1700
Data Index: 6157798 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8136. Min Range: -9.8136
Max Act: 8.6886. Min Act: -0.1700
Data Index: 1606200 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8136. Min Range: -9.8136
Max Act: 8.6886. Min Act: -0.1700
Data Index: 3388300 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8136. Min Range: -9.8136
Max Act: 8.6886. Min Act: -0.1700
Data Index: 6772314 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8136. Min Range: -9.8136
Max Act: 8.7511. Min Act: -0.1700
Data Index: 5215206 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8136. Min Range: -9.8136
Max Act: 8.6261. Min Act: -0.1700
Data Index: 7710689 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8136. Min Range: -9.8136
Max Act: 8.6261. Min Act: -0.1700
Data Index: 7217303 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #19