Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6200 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4952. Min Range: -7.4952
Max Act: 7.4952. Min Act: -0.1700
Data Index: 8526022 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4952. Min Range: -7.4952
Max Act: 7.1827. Min Act: -0.1700
Data Index: 3781248 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4952. Min Range: -7.4952
Max Act: 6.9639. Min Act: -0.1700
Data Index: 7635402 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4952. Min Range: -7.4952
Max Act: 6.9327. Min Act: -0.1700
Data Index: 7213656 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4952. Min Range: -7.4952
Max Act: 6.8702. Min Act: -0.1700
Data Index: 4767453 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4952. Min Range: -7.4952
Max Act: 6.8077. Min Act: -0.1700
Data Index: 8685475 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4952. Min Range: -7.4952
Max Act: 6.8077. Min Act: -0.1700
Data Index: 5270425 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4952. Min Range: -7.4952
Max Act: 6.8077. Min Act: -0.1700
Data Index: 1136439 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4952. Min Range: -7.4952
Max Act: 6.7452. Min Act: -0.1700
Data Index: 7723529 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4952. Min Range: -7.4952
Max Act: 6.7452. Min Act: -0.1700
Data Index: 6216555 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4952. Min Range: -7.4952
Max Act: 6.7452. Min Act: -0.1700
Data Index: 624587 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4952. Min Range: -7.4952
Max Act: 6.6827. Min Act: -0.1700
Data Index: 7602089 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4952. Min Range: -7.4952
Max Act: 6.6514. Min Act: -0.1700
Data Index: 3812228 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4952. Min Range: -7.4952
Max Act: 6.6514. Min Act: -0.1700
Data Index: 3649033 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4952. Min Range: -7.4952
Max Act: 6.6514. Min Act: -0.1700
Data Index: 1180696 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4952. Min Range: -7.4952
Max Act: 6.6202. Min Act: -0.1700
Data Index: 5968426 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4952. Min Range: -7.4952
Max Act: 6.5577. Min Act: -0.1700
Data Index: 4934146 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4952. Min Range: -7.4952
Max Act: 6.5889. Min Act: -0.1700
Data Index: 6293412 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4952. Min Range: -7.4952
Max Act: 6.5889. Min Act: -0.1700
Data Index: 8583189 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4952. Min Range: -7.4952
Max Act: 6.5889. Min Act: -0.1700
Data Index: 5881302 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19