Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3892 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9934. Min Range: -5.9934
Max Act: 5.9934. Min Act: -0.1685
Data Index: 1522897 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9934. Min Range: -5.9934
Max Act: 5.9309. Min Act: -0.1700
Data Index: 7074575 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9934. Min Range: -5.9934
Max Act: 5.8997. Min Act: -0.1700
Data Index: 3279818 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9934. Min Range: -5.9934
Max Act: 5.5872. Min Act: -0.1700
Data Index: 350825 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9934. Min Range: -5.9934
Max Act: 5.5872. Min Act: -0.1700
Data Index: 1771669 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9934. Min Range: -5.9934
Max Act: 5.5872. Min Act: -0.1700
Data Index: 5697340 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9934. Min Range: -5.9934
Max Act: 5.5559. Min Act: -0.1700
Data Index: 5329167 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9934. Min Range: -5.9934
Max Act: 5.5559. Min Act: -0.1699
Data Index: 3499981 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9934. Min Range: -5.9934
Max Act: 5.5559. Min Act: -0.1700
Data Index: 7210260 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9934. Min Range: -5.9934
Max Act: 5.5559. Min Act: -0.1700
Data Index: 6182550 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9934. Min Range: -5.9934
Max Act: 5.5247. Min Act: -0.1700
Data Index: 8366124 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9934. Min Range: -5.9934
Max Act: 5.5247. Min Act: -0.1700
Data Index: 7275727 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9934. Min Range: -5.9934
Max Act: 5.4934. Min Act: -0.1700
Data Index: 8149808 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9934. Min Range: -5.9934
Max Act: 5.4934. Min Act: -0.1700
Data Index: 6051297 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9934. Min Range: -5.9934
Max Act: 5.4622. Min Act: -0.1700
Data Index: 5061948 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9934. Min Range: -5.9934
Max Act: 5.4309. Min Act: -0.1700
Data Index: 6699856 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9934. Min Range: -5.9934
Max Act: 5.4622. Min Act: -0.1700
Data Index: 4593533 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9934. Min Range: -5.9934
Max Act: 5.4622. Min Act: -0.1700
Data Index: 1068310 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9934. Min Range: -5.9934
Max Act: 5.4622. Min Act: -0.1700
Data Index: 4578242 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9934. Min Range: -5.9934
Max Act: 5.4309. Min Act: -0.1700
Data Index: 3478717 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19