Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5544 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3763. Min Range: -6.3763
Max Act: 6.3763. Min Act: -0.1700
Data Index: 4602444 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3763. Min Range: -6.3763
Max Act: 6.3138. Min Act: -0.1700
Data Index: 5768638 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3763. Min Range: -6.3763
Max Act: 6.0638. Min Act: -0.1700
Data Index: 5173321 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3763. Min Range: -6.3763
Max Act: 6.0325. Min Act: -0.1700
Data Index: 910101 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3763. Min Range: -6.3763
Max Act: 6.0013. Min Act: -0.1700
Data Index: 8359835 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3763. Min Range: -6.3763
Max Act: 6.0013. Min Act: -0.1697
Data Index: 245478 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3763. Min Range: -6.3763
Max Act: 6.0325. Min Act: -0.1700
Data Index: 643270 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3763. Min Range: -6.3763
Max Act: 5.9388. Min Act: -0.1700
Data Index: 870616 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3763. Min Range: -6.3763
Max Act: 5.9388. Min Act: -0.1700
Data Index: 5715353 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3763. Min Range: -6.3763
Max Act: 5.9075. Min Act: -0.1700
Data Index: 691238 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3763. Min Range: -6.3763
Max Act: 5.8763. Min Act: -0.1700
Data Index: 1701283 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3763. Min Range: -6.3763
Max Act: 5.8763. Min Act: -0.1700
Data Index: 4991821 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3763. Min Range: -6.3763
Max Act: 5.9075. Min Act: -0.1700
Data Index: 1183906 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3763. Min Range: -6.3763
Max Act: 5.8450. Min Act: -0.1700
Data Index: 6348952 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3763. Min Range: -6.3763
Max Act: 5.8138. Min Act: -0.1700
Data Index: 888343 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3763. Min Range: -6.3763
Max Act: 5.8138. Min Act: -0.1700
Data Index: 3781266 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3763. Min Range: -6.3763
Max Act: 5.8450. Min Act: -0.1700
Data Index: 2718169 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3763. Min Range: -6.3763
Max Act: 5.8138. Min Act: -0.1700
Data Index: 6571472 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3763. Min Range: -6.3763
Max Act: 5.8138. Min Act: -0.1700
Data Index: 4397215 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3763. Min Range: -6.3763
Max Act: 5.7825. Min Act: -0.1700
Data Index: 5324220 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19