Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6110 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5692. Min Range: -7.5692
Max Act: 7.5692. Min Act: -0.1700
Data Index: 8115904 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5692. Min Range: -7.5692
Max Act: 7.4130. Min Act: -0.1700
Data Index: 8043445 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5692. Min Range: -7.5692
Max Act: 7.4130. Min Act: -0.1700
Data Index: 552940 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5692. Min Range: -7.5692
Max Act: 7.3817. Min Act: -0.1700
Data Index: 4267279 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5692. Min Range: -7.5692
Max Act: 7.3192. Min Act: -0.1700
Data Index: 7696092 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5692. Min Range: -7.5692
Max Act: 7.2880. Min Act: -0.1700
Data Index: 2963302 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5692. Min Range: -7.5692
Max Act: 7.1942. Min Act: -0.1700
Data Index: 8773559 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5692. Min Range: -7.5692
Max Act: 7.1942. Min Act: -0.1700
Data Index: 1768848 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5692. Min Range: -7.5692
Max Act: 7.1630. Min Act: -0.1700
Data Index: 1228408 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5692. Min Range: -7.5692
Max Act: 7.1317. Min Act: -0.1700
Data Index: 7785024 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5692. Min Range: -7.5692
Max Act: 7.0692. Min Act: -0.1700
Data Index: 7284999 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5692. Min Range: -7.5692
Max Act: 7.0380. Min Act: -0.1700
Data Index: 7454939 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5692. Min Range: -7.5692
Max Act: 7.0380. Min Act: -0.1700
Data Index: 521493 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5692. Min Range: -7.5692
Max Act: 7.0380. Min Act: -0.1700
Data Index: 8100898 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5692. Min Range: -7.5692
Max Act: 7.0067. Min Act: -0.1700
Data Index: 7319257 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5692. Min Range: -7.5692
Max Act: 7.0067. Min Act: -0.1700
Data Index: 6887308 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5692. Min Range: -7.5692
Max Act: 6.9755. Min Act: -0.1700
Data Index: 2778029 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5692. Min Range: -7.5692
Max Act: 6.9755. Min Act: -0.1700
Data Index: 314542 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5692. Min Range: -7.5692
Max Act: 6.9442. Min Act: -0.1700
Data Index: 8663969 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5692. Min Range: -7.5692
Max Act: 6.9442. Min Act: -0.1700
Data Index: 6283599 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19