Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2855 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0715. Min Range: -7.0715
Max Act: 7.0715. Min Act: -0.1700
Data Index: 5491074 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0715. Min Range: -7.0715
Max Act: 7.0402. Min Act: -0.1700
Data Index: 4284471 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0715. Min Range: -7.0715
Max Act: 7.0402. Min Act: -0.1700
Data Index: 5333820 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0715. Min Range: -7.0715
Max Act: 7.0090. Min Act: -0.1700
Data Index: 2922184 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0715. Min Range: -7.0715
Max Act: 6.9777. Min Act: -0.1700
Data Index: 6738827 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0715. Min Range: -7.0715
Max Act: 6.9152. Min Act: -0.1700
Data Index: 5383827 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0715. Min Range: -7.0715
Max Act: 6.9152. Min Act: -0.1700
Data Index: 1635524 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0715. Min Range: -7.0715
Max Act: 6.9152. Min Act: -0.1700
Data Index: 2566993 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0715. Min Range: -7.0715
Max Act: 6.8840. Min Act: -0.1700
Data Index: 4248883 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0715. Min Range: -7.0715
Max Act: 6.8840. Min Act: -0.1700
Data Index: 1763718 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0715. Min Range: -7.0715
Max Act: 6.8840. Min Act: -0.1700
Data Index: 2927811 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0715. Min Range: -7.0715
Max Act: 6.8840. Min Act: -0.1700
Data Index: 5698204 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0715. Min Range: -7.0715
Max Act: 6.8840. Min Act: -0.1700
Data Index: 5763066 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0715. Min Range: -7.0715
Max Act: 6.9152. Min Act: -0.1700
Data Index: 3174664 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0715. Min Range: -7.0715
Max Act: 6.8527. Min Act: -0.1700
Data Index: 8332471 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0715. Min Range: -7.0715
Max Act: 6.8215. Min Act: -0.1700
Data Index: 4725378 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0715. Min Range: -7.0715
Max Act: 6.8527. Min Act: -0.1700
Data Index: 6063139 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0715. Min Range: -7.0715
Max Act: 6.8527. Min Act: -0.1700
Data Index: 8160383 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0715. Min Range: -7.0715
Max Act: 6.7902. Min Act: -0.1700
Data Index: 3173118 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0715. Min Range: -7.0715
Max Act: 6.7902. Min Act: -0.1700
Data Index: 1635111 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19