Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3335 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3174. Min Range: -6.3174
Max Act: 6.3174. Min Act: -0.1700
Data Index: 5787887 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3174. Min Range: -6.3174
Max Act: 6.2236. Min Act: -0.1700
Data Index: 1690305 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3174. Min Range: -6.3174
Max Act: 5.9424. Min Act: -0.1700
Data Index: 5085198 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3174. Min Range: -6.3174
Max Act: 5.9424. Min Act: -0.1700
Data Index: 6873305 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3174. Min Range: -6.3174
Max Act: 5.9111. Min Act: -0.1700
Data Index: 554662 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3174. Min Range: -6.3174
Max Act: 5.9111. Min Act: -0.1700
Data Index: 3473269 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3174. Min Range: -6.3174
Max Act: 5.9111. Min Act: -0.1700
Data Index: 5526464 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3174. Min Range: -6.3174
Max Act: 5.8174. Min Act: -0.1700
Data Index: 1355813 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3174. Min Range: -6.3174
Max Act: 5.7861. Min Act: -0.1700
Data Index: 6849436 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3174. Min Range: -6.3174
Max Act: 5.7861. Min Act: -0.1700
Data Index: 5021747 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3174. Min Range: -6.3174
Max Act: 5.8174. Min Act: -0.1700
Data Index: 7180248 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3174. Min Range: -6.3174
Max Act: 5.7549. Min Act: -0.1700
Data Index: 8130890 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3174. Min Range: -6.3174
Max Act: 5.8174. Min Act: -0.1700
Data Index: 7795200 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3174. Min Range: -6.3174
Max Act: 5.7861. Min Act: -0.1700
Data Index: 3305698 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3174. Min Range: -6.3174
Max Act: 5.7549. Min Act: -0.1700
Data Index: 7438897 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3174. Min Range: -6.3174
Max Act: 5.7549. Min Act: -0.1700
Data Index: 2995518 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3174. Min Range: -6.3174
Max Act: 5.7549. Min Act: -0.1700
Data Index: 7305451 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3174. Min Range: -6.3174
Max Act: 5.7236. Min Act: -0.1700
Data Index: 1250484 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3174. Min Range: -6.3174
Max Act: 5.7236. Min Act: -0.1700
Data Index: 8120304 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3174. Min Range: -6.3174
Max Act: 5.7236. Min Act: -0.1700
Data Index: 5875281 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19