Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2333 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9933. Min Range: -4.9933
Max Act: 4.9933. Min Act: -0.1700
Data Index: 8017119 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9933. Min Range: -4.9933
Max Act: 4.9620. Min Act: -0.1700
Data Index: 3681789 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9933. Min Range: -4.9933
Max Act: 4.8995. Min Act: -0.1700
Data Index: 8102704 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9933. Min Range: -4.9933
Max Act: 4.8995. Min Act: -0.1700
Data Index: 1885304 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9933. Min Range: -4.9933
Max Act: 4.8683. Min Act: -0.1700
Data Index: 6544781 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9933. Min Range: -4.9933
Max Act: 4.8683. Min Act: -0.1700
Data Index: 8794112 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9933. Min Range: -4.9933
Max Act: 4.8683. Min Act: -0.1700
Data Index: 7293916 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9933. Min Range: -4.9933
Max Act: 4.8683. Min Act: -0.1700
Data Index: 5341594 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9933. Min Range: -4.9933
Max Act: 4.8683. Min Act: -0.1700
Data Index: 7392585 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9933. Min Range: -4.9933
Max Act: 4.8995. Min Act: -0.1700
Data Index: 7548025 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9933. Min Range: -4.9933
Max Act: 4.8370. Min Act: -0.1700
Data Index: 7523179 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9933. Min Range: -4.9933
Max Act: 4.8370. Min Act: -0.1700
Data Index: 781249 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9933. Min Range: -4.9933
Max Act: 4.8370. Min Act: -0.1700
Data Index: 4920429 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9933. Min Range: -4.9933
Max Act: 4.8058. Min Act: -0.1700
Data Index: 3844716 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9933. Min Range: -4.9933
Max Act: 4.8370. Min Act: -0.1700
Data Index: 1227596 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9933. Min Range: -4.9933
Max Act: 4.8370. Min Act: -0.1700
Data Index: 2861697 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9933. Min Range: -4.9933
Max Act: 4.8058. Min Act: -0.1700
Data Index: 4841608 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9933. Min Range: -4.9933
Max Act: 4.8058. Min Act: -0.1700
Data Index: 1835368 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9933. Min Range: -4.9933
Max Act: 4.8370. Min Act: -0.1700
Data Index: 2763821 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9933. Min Range: -4.9933
Max Act: 4.8058. Min Act: -0.1700
Data Index: 2224407 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19