Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2904 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 6.2070. Min Range: -6.2070
Max Act: 6.2070. Min Act: -0.1700
Data Index: 7187483 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2070. Min Range: -6.2070
Max Act: 6.1132. Min Act: -0.1700
Data Index: 8435807 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2070. Min Range: -6.2070
Max Act: 6.0195. Min Act: -0.1700
Data Index: 8623053 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2070. Min Range: -6.2070
Max Act: 6.0195. Min Act: -0.1700
Data Index: 4988263 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2070. Min Range: -6.2070
Max Act: 5.9882. Min Act: -0.1700
Data Index: 5585578 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2070. Min Range: -6.2070
Max Act: 5.9882. Min Act: -0.1700
Data Index: 2564420 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2070. Min Range: -6.2070
Max Act: 5.9882. Min Act: -0.1700
Data Index: 7407190 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2070. Min Range: -6.2070
Max Act: 5.9570. Min Act: -0.1700
Data Index: 8197032 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2070. Min Range: -6.2070
Max Act: 5.9257. Min Act: -0.1700
Data Index: 7857005 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2070. Min Range: -6.2070
Max Act: 5.9257. Min Act: -0.1700
Data Index: 3924420 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2070. Min Range: -6.2070
Max Act: 5.9570. Min Act: -0.1700
Data Index: 8067620 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2070. Min Range: -6.2070
Max Act: 5.9257. Min Act: -0.1700
Data Index: 2048276 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2070. Min Range: -6.2070
Max Act: 5.8945. Min Act: -0.1700
Data Index: 360312 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2070. Min Range: -6.2070
Max Act: 5.8320. Min Act: -0.1700
Data Index: 3423442 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2070. Min Range: -6.2070
Max Act: 5.8632. Min Act: -0.1700
Data Index: 6685373 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2070. Min Range: -6.2070
Max Act: 5.8007. Min Act: -0.1700
Data Index: 4508913 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2070. Min Range: -6.2070
Max Act: 5.8320. Min Act: -0.1700
Data Index: 2573814 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2070. Min Range: -6.2070
Max Act: 5.8320. Min Act: -0.1700
Data Index: 2619832 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2070. Min Range: -6.2070
Max Act: 5.8320. Min Act: -0.1700
Data Index: 1567547 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2070. Min Range: -6.2070
Max Act: 5.7382. Min Act: -0.1700
Data Index: 3981621 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19