Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3548 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3994. Min Range: -5.3994
Max Act: 5.3994. Min Act: -0.1700
Data Index: 6136578 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3994. Min Range: -5.3994
Max Act: 5.3994. Min Act: -0.1700
Data Index: 1029083 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3994. Min Range: -5.3994
Max Act: 5.3994. Min Act: -0.1700
Data Index: 4599149 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3994. Min Range: -5.3994
Max Act: 5.1494. Min Act: -0.1700
Data Index: 3384429 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3994. Min Range: -5.3994
Max Act: 4.9307. Min Act: -0.1700
Data Index: 1776092 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3994. Min Range: -5.3994
Max Act: 4.8994. Min Act: -0.1700
Data Index: 8449414 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3994. Min Range: -5.3994
Max Act: 4.8994. Min Act: -0.1700
Data Index: 8134501 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3994. Min Range: -5.3994
Max Act: 4.8682. Min Act: -0.1700
Data Index: 3907789 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3994. Min Range: -5.3994
Max Act: 4.8369. Min Act: -0.1700
Data Index: 565923 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3994. Min Range: -5.3994
Max Act: 4.7744. Min Act: -0.1700
Data Index: 3485281 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3994. Min Range: -5.3994
Max Act: 4.8057. Min Act: -0.1700
Data Index: 3733040 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3994. Min Range: -5.3994
Max Act: 4.7744. Min Act: -0.1700
Data Index: 3240184 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3994. Min Range: -5.3994
Max Act: 4.7744. Min Act: -0.1700
Data Index: 4718370 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3994. Min Range: -5.3994
Max Act: 4.7119. Min Act: -0.1700
Data Index: 586322 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3994. Min Range: -5.3994
Max Act: 4.7432. Min Act: -0.1700
Data Index: 722067 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3994. Min Range: -5.3994
Max Act: 4.7119. Min Act: -0.1700
Data Index: 8188958 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3994. Min Range: -5.3994
Max Act: 4.7119. Min Act: -0.1700
Data Index: 384404 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3994. Min Range: -5.3994
Max Act: 4.7119. Min Act: -0.1700
Data Index: 8065180 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3994. Min Range: -5.3994
Max Act: 4.6807. Min Act: -0.1700
Data Index: 2246943 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3994. Min Range: -5.3994
Max Act: 4.6807. Min Act: -0.1700
Data Index: 5325770 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19