Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2717 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0507. Min Range: -4.0507
Max Act: 4.0507. Min Act: -0.1700
Data Index: 6035521 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0507. Min Range: -4.0507
Max Act: 3.9882. Min Act: -0.1700
Data Index: 6583018 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0507. Min Range: -4.0507
Max Act: 3.9257. Min Act: -0.1700
Data Index: 5463719 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0507. Min Range: -4.0507
Max Act: 3.8944. Min Act: -0.1700
Data Index: 8394634 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0507. Min Range: -4.0507
Max Act: 3.8632. Min Act: -0.1700
Data Index: 7140972 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0507. Min Range: -4.0507
Max Act: 3.8632. Min Act: -0.1700
Data Index: 3901332 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0507. Min Range: -4.0507
Max Act: 3.8632. Min Act: -0.1700
Data Index: 8206541 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0507. Min Range: -4.0507
Max Act: 3.8319. Min Act: -0.1700
Data Index: 5190043 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0507. Min Range: -4.0507
Max Act: 3.8006. Min Act: -0.1700
Data Index: 4807474 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0507. Min Range: -4.0507
Max Act: 3.8006. Min Act: -0.1700
Data Index: 2168302 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0507. Min Range: -4.0507
Max Act: 3.8006. Min Act: -0.1700
Data Index: 1916430 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0507. Min Range: -4.0507
Max Act: 3.7693. Min Act: -0.1700
Data Index: 8154597 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0507. Min Range: -4.0507
Max Act: 3.7537. Min Act: -0.1700
Data Index: 6878429 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0507. Min Range: -4.0507
Max Act: 3.7537. Min Act: -0.1700
Data Index: 3415567 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0507. Min Range: -4.0507
Max Act: 3.7537. Min Act: -0.1700
Data Index: 5190042 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0507. Min Range: -4.0507
Max Act: 3.7693. Min Act: -0.1700
Data Index: 6530066 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0507. Min Range: -4.0507
Max Act: 3.7537. Min Act: -0.1700
Data Index: 6648489 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0507. Min Range: -4.0507
Max Act: 3.7537. Min Act: -0.1700
Data Index: 1458105 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0507. Min Range: -4.0507
Max Act: 3.7537. Min Act: -0.1700
Data Index: 5988815 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0507. Min Range: -4.0507
Max Act: 3.7381. Min Act: -0.1700
Data Index: 2427330 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19