Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5425 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0818. Min Range: -6.0818
Max Act: 6.0818. Min Act: -0.1700
Data Index: 6849234 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0818. Min Range: -6.0818
Max Act: 5.9568. Min Act: -0.1700
Data Index: 6363756 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0818. Min Range: -6.0818
Max Act: 5.8318. Min Act: -0.1700
Data Index: 491809 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0818. Min Range: -6.0818
Max Act: 5.7693. Min Act: -0.1700
Data Index: 4648253 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0818. Min Range: -6.0818
Max Act: 5.7693. Min Act: -0.1700
Data Index: 3089206 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0818. Min Range: -6.0818
Max Act: 5.7693. Min Act: -0.1700
Data Index: 946804 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0818. Min Range: -6.0818
Max Act: 5.7693. Min Act: -0.1700
Data Index: 8359007 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0818. Min Range: -6.0818
Max Act: 5.7068. Min Act: -0.1700
Data Index: 1873705 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0818. Min Range: -6.0818
Max Act: 5.7068. Min Act: -0.1700
Data Index: 2079703 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0818. Min Range: -6.0818
Max Act: 5.7068. Min Act: -0.1700
Data Index: 4829869 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0818. Min Range: -6.0818
Max Act: 5.6756. Min Act: -0.1700
Data Index: 5170416 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0818. Min Range: -6.0818
Max Act: 5.6756. Min Act: -0.1700
Data Index: 3997964 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0818. Min Range: -6.0818
Max Act: 5.6443. Min Act: -0.1700
Data Index: 5496500 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0818. Min Range: -6.0818
Max Act: 5.6443. Min Act: -0.1700
Data Index: 7752237 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0818. Min Range: -6.0818
Max Act: 5.6443. Min Act: -0.1700
Data Index: 2921846 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0818. Min Range: -6.0818
Max Act: 5.6443. Min Act: -0.1700
Data Index: 1165378 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0818. Min Range: -6.0818
Max Act: 5.6443. Min Act: -0.1700
Data Index: 5170415 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0818. Min Range: -6.0818
Max Act: 5.6443. Min Act: -0.1700
Data Index: 3190279 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0818. Min Range: -6.0818
Max Act: 5.6131. Min Act: -0.1700
Data Index: 1536706 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0818. Min Range: -6.0818
Max Act: 5.6443. Min Act: -0.1700
Data Index: 2583658 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19