Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3394 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9567. Min Range: -6.9567
Max Act: 6.9567. Min Act: -0.1700
Data Index: 5977662 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9567. Min Range: -6.9567
Max Act: 6.4880. Min Act: -0.1700
Data Index: 7346142 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9567. Min Range: -6.9567
Max Act: 6.3630. Min Act: -0.1700
Data Index: 7184590 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9567. Min Range: -6.9567
Max Act: 6.3630. Min Act: -0.1700
Data Index: 2938928 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9567. Min Range: -6.9567
Max Act: 6.3630. Min Act: -0.1700
Data Index: 784382 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9567. Min Range: -6.9567
Max Act: 6.3005. Min Act: -0.1700
Data Index: 4905892 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9567. Min Range: -6.9567
Max Act: 6.2692. Min Act: -0.1700
Data Index: 651832 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9567. Min Range: -6.9567
Max Act: 6.2380. Min Act: -0.1700
Data Index: 4571319 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9567. Min Range: -6.9567
Max Act: 6.2067. Min Act: -0.1700
Data Index: 1967752 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9567. Min Range: -6.9567
Max Act: 6.2067. Min Act: -0.1700
Data Index: 7681415 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9567. Min Range: -6.9567
Max Act: 6.1130. Min Act: -0.1700
Data Index: 4848770 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9567. Min Range: -6.9567
Max Act: 6.0505. Min Act: -0.1700
Data Index: 6866006 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9567. Min Range: -6.9567
Max Act: 6.0505. Min Act: -0.1700
Data Index: 5254945 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9567. Min Range: -6.9567
Max Act: 6.0505. Min Act: -0.1700
Data Index: 8293638 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9567. Min Range: -6.9567
Max Act: 6.0192. Min Act: -0.1700
Data Index: 3043220 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9567. Min Range: -6.9567
Max Act: 6.0192. Min Act: -0.1700
Data Index: 3907539 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9567. Min Range: -6.9567
Max Act: 5.9880. Min Act: -0.1700
Data Index: 1620687 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9567. Min Range: -6.9567
Max Act: 5.9567. Min Act: -0.1700
Data Index: 6022624 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9567. Min Range: -6.9567
Max Act: 5.9567. Min Act: -0.1700
Data Index: 6269518 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9567. Min Range: -6.9567
Max Act: 5.9567. Min Act: -0.1700
Data Index: 5486527 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #19