Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5437 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.5934. Min Range: -1.5934
Max Act: 1.5934. Min Act: -0.1700
Data Index: 4532158 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5934. Min Range: -1.5934
Max Act: 1.5409. Min Act: -0.1700
Data Index: 1235426 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5934. Min Range: -1.5934
Max Act: 1.5409. Min Act: -0.1697
Data Index: 874504 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5934. Min Range: -1.5934
Max Act: 1.5233. Min Act: -0.1698
Data Index: 4309658 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5934. Min Range: -1.5934
Max Act: 1.5233. Min Act: -0.1700
Data Index: 3288574 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5934. Min Range: -1.5934
Max Act: 1.5233. Min Act: -0.1700
Data Index: 244826 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5934. Min Range: -1.5934
Max Act: 1.4882. Min Act: -0.1700
Data Index: 3001332 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5934. Min Range: -1.5934
Max Act: 1.5058. Min Act: -0.1699
Data Index: 593122 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5934. Min Range: -1.5934
Max Act: 1.4882. Min Act: -0.1697
Data Index: 5127756 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5934. Min Range: -1.5934
Max Act: 1.4882. Min Act: -0.1698
Data Index: 5043529 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5934. Min Range: -1.5934
Max Act: 1.5058. Min Act: -0.1663
Data Index: 6453271 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5934. Min Range: -1.5934
Max Act: 1.4707. Min Act: -0.1700
Data Index: 5356941 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5934. Min Range: -1.5934
Max Act: 1.4355. Min Act: -0.1696
Data Index: 7898879 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5934. Min Range: -1.5934
Max Act: 1.4531. Min Act: -0.1694
Data Index: 3171957 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5934. Min Range: -1.5934
Max Act: 1.4355. Min Act: -0.1700
Data Index: 7004225 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5934. Min Range: -1.5934
Max Act: 1.4531. Min Act: -0.1700
Data Index: 2869492 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5934. Min Range: -1.5934
Max Act: 1.4531. Min Act: -0.1700
Data Index: 2078705 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5934. Min Range: -1.5934
Max Act: 1.4355. Min Act: -0.1700
Data Index: 3797471 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5934. Min Range: -1.5934
Max Act: 1.4355. Min Act: -0.1681
Data Index: 5189224 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5934. Min Range: -1.5934
Max Act: 1.4355. Min Act: -0.1700
Data Index: 3129165 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19