Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 788 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.1171. Min Range: -4.1171
Max Act: 4.1171. Min Act: -0.1700
Data Index: 4231495 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1171. Min Range: -4.1171
Max Act: 4.0858. Min Act: -0.1700
Data Index: 1430781 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1171. Min Range: -4.1171
Max Act: 4.0233. Min Act: -0.1700
Data Index: 4987855 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1171. Min Range: -4.1171
Max Act: 3.9608. Min Act: -0.1700
Data Index: 8092388 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1171. Min Range: -4.1171
Max Act: 3.9608. Min Act: -0.1700
Data Index: 3233802 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1171. Min Range: -4.1171
Max Act: 3.9295. Min Act: -0.1700
Data Index: 7948198 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1171. Min Range: -4.1171
Max Act: 3.9295. Min Act: -0.1700
Data Index: 4288655 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1171. Min Range: -4.1171
Max Act: 3.8983. Min Act: -0.1700
Data Index: 7666948 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1171. Min Range: -4.1171
Max Act: 3.8670. Min Act: -0.1700
Data Index: 715787 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1171. Min Range: -4.1171
Max Act: 3.8670. Min Act: -0.1700
Data Index: 268937 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1171. Min Range: -4.1171
Max Act: 3.8045. Min Act: -0.1700
Data Index: 4712227 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1171. Min Range: -4.1171
Max Act: 3.8357. Min Act: -0.1700
Data Index: 7738392 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1171. Min Range: -4.1171
Max Act: 3.8357. Min Act: -0.1700
Data Index: 2678080 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1171. Min Range: -4.1171
Max Act: 3.8357. Min Act: -0.1700
Data Index: 7056081 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1171. Min Range: -4.1171
Max Act: 3.8357. Min Act: -0.1700
Data Index: 948156 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1171. Min Range: -4.1171
Max Act: 3.8357. Min Act: -0.1700
Data Index: 2435031 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1171. Min Range: -4.1171
Max Act: 3.8670. Min Act: -0.1700
Data Index: 1752366 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1171. Min Range: -4.1171
Max Act: 3.8045. Min Act: -0.1700
Data Index: 6312813 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1171. Min Range: -4.1171
Max Act: 3.8045. Min Act: -0.1700
Data Index: 4380022 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1171. Min Range: -4.1171
Max Act: 3.8045. Min Act: -0.1700
Data Index: 4173306 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19