Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2915 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.4066. Min Act: -0.1700
Data Index: 7353447 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.4066. Min Act: -0.1700
Data Index: 7185206 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.3441. Min Act: -0.1700
Data Index: 730601 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.3128. Min Act: -0.1700
Data Index: 8200249 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.2503. Min Act: -0.1700
Data Index: 4838548 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.2191. Min Act: -0.1700
Data Index: 4424939 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.2191. Min Act: -0.1700
Data Index: 7353450 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.2191. Min Act: -0.1700
Data Index: 4877744 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.2191. Min Act: -0.1700
Data Index: 7185205 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.2191. Min Act: -0.1700
Data Index: 4458501 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.1878. Min Act: -0.1700
Data Index: 7006695 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.1878. Min Act: -0.1700
Data Index: 3617560 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.1878. Min Act: -0.1700
Data Index: 6275618 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.1566. Min Act: -0.1700
Data Index: 7204948 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.1566. Min Act: -0.1700
Data Index: 5566906 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.1566. Min Act: -0.1700
Data Index: 4414725 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.1253. Min Act: -0.1700
Data Index: 4757620 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.1253. Min Act: -0.1700
Data Index: 4136458 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.1253. Min Act: -0.1700
Data Index: 1815525 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.1253. Min Act: -0.1700
Data Index: 5477255 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19