Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2554 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3765. Min Range: -6.3765
Max Act: 6.3765. Min Act: -0.1700
Data Index: 2029081 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3765. Min Range: -6.3765
Max Act: 5.5328. Min Act: -0.1700
Data Index: 6649886 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3765. Min Range: -6.3765
Max Act: 5.4078. Min Act: -0.1700
Data Index: 7675403 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3765. Min Range: -6.3765
Max Act: 5.3453. Min Act: -0.1700
Data Index: 7483942 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3765. Min Range: -6.3765
Max Act: 5.3453. Min Act: -0.1700
Data Index: 5202075 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3765. Min Range: -6.3765
Max Act: 5.3765. Min Act: -0.1700
Data Index: 589910 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3765. Min Range: -6.3765
Max Act: 5.3140. Min Act: -0.1700
Data Index: 1241732 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3765. Min Range: -6.3765
Max Act: 5.3453. Min Act: -0.1700
Data Index: 8514300 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3765. Min Range: -6.3765
Max Act: 5.2203. Min Act: -0.1700
Data Index: 1546323 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3765. Min Range: -6.3765
Max Act: 5.2203. Min Act: -0.1700
Data Index: 3574995 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3765. Min Range: -6.3765
Max Act: 5.1578. Min Act: -0.1700
Data Index: 407086 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3765. Min Range: -6.3765
Max Act: 5.1890. Min Act: -0.1700
Data Index: 4617576 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3765. Min Range: -6.3765
Max Act: 5.1578. Min Act: -0.1700
Data Index: 4492858 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3765. Min Range: -6.3765
Max Act: 5.1890. Min Act: -0.1700
Data Index: 5942118 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3765. Min Range: -6.3765
Max Act: 5.1265. Min Act: -0.1700
Data Index: 5730316 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3765. Min Range: -6.3765
Max Act: 5.1265. Min Act: -0.1700
Data Index: 3508698 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3765. Min Range: -6.3765
Max Act: 5.1265. Min Act: -0.1700
Data Index: 5991961 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3765. Min Range: -6.3765
Max Act: 5.0640. Min Act: -0.1700
Data Index: 8700094 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3765. Min Range: -6.3765
Max Act: 5.0640. Min Act: -0.1700
Data Index: 8017087 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3765. Min Range: -6.3765
Max Act: 5.0640. Min Act: -0.1700
Data Index: 5277037 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19