Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2906 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3174. Min Range: -7.3174
Max Act: 7.3174. Min Act: -0.1700
Data Index: 1232153 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3174. Min Range: -7.3174
Max Act: 7.2549. Min Act: -0.1700
Data Index: 2208229 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3174. Min Range: -7.3174
Max Act: 7.2549. Min Act: -0.1700
Data Index: 3721602 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3174. Min Range: -7.3174
Max Act: 7.2237. Min Act: -0.1700
Data Index: 2792315 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3174. Min Range: -7.3174
Max Act: 7.2237. Min Act: -0.1700
Data Index: 856893 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3174. Min Range: -7.3174
Max Act: 7.1924. Min Act: -0.1700
Data Index: 3863198 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3174. Min Range: -7.3174
Max Act: 7.0674. Min Act: -0.1700
Data Index: 3326022 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3174. Min Range: -7.3174
Max Act: 7.0362. Min Act: -0.1700
Data Index: 6055755 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3174. Min Range: -7.3174
Max Act: 7.0362. Min Act: -0.1700
Data Index: 1749341 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3174. Min Range: -7.3174
Max Act: 7.0362. Min Act: -0.1700
Data Index: 758428 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3174. Min Range: -7.3174
Max Act: 6.9737. Min Act: -0.1700
Data Index: 6886003 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3174. Min Range: -7.3174
Max Act: 6.9737. Min Act: -0.1700
Data Index: 5472030 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3174. Min Range: -7.3174
Max Act: 6.9737. Min Act: -0.1700
Data Index: 8317099 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3174. Min Range: -7.3174
Max Act: 6.9424. Min Act: -0.1700
Data Index: 6548007 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3174. Min Range: -7.3174
Max Act: 6.9424. Min Act: -0.1700
Data Index: 6067 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3174. Min Range: -7.3174
Max Act: 6.9112. Min Act: -0.1700
Data Index: 6886004 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3174. Min Range: -7.3174
Max Act: 6.9112. Min Act: -0.1700
Data Index: 906643 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3174. Min Range: -7.3174
Max Act: 6.8487. Min Act: -0.1700
Data Index: 3684032 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3174. Min Range: -7.3174
Max Act: 6.8174. Min Act: -0.1700
Data Index: 3017271 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3174. Min Range: -7.3174
Max Act: 6.8487. Min Act: -0.1700
Data Index: 761931 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19