Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2032 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7075. Min Range: -6.7075
Max Act: 6.7075. Min Act: -0.1700
Data Index: 3088999 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7075. Min Range: -6.7075
Max Act: 6.3638. Min Act: -0.1700
Data Index: 2979158 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7075. Min Range: -6.7075
Max Act: 6.3325. Min Act: -0.1700
Data Index: 6300192 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7075. Min Range: -6.7075
Max Act: 6.3013. Min Act: -0.1700
Data Index: 1172167 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7075. Min Range: -6.7075
Max Act: 6.2700. Min Act: -0.1700
Data Index: 6738908 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7075. Min Range: -6.7075
Max Act: 6.2075. Min Act: -0.1700
Data Index: 1663139 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7075. Min Range: -6.7075
Max Act: 6.1763. Min Act: -0.1700
Data Index: 5266549 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7075. Min Range: -6.7075
Max Act: 6.1450. Min Act: -0.1700
Data Index: 3074662 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7075. Min Range: -6.7075
Max Act: 6.1138. Min Act: -0.1700
Data Index: 2965838 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7075. Min Range: -6.7075
Max Act: 6.1138. Min Act: -0.1700
Data Index: 7258109 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7075. Min Range: -6.7075
Max Act: 6.0825. Min Act: -0.1700
Data Index: 3155672 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7075. Min Range: -6.7075
Max Act: 6.0825. Min Act: -0.1700
Data Index: 248597 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7075. Min Range: -6.7075
Max Act: 6.0513. Min Act: -0.1700
Data Index: 5187748 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7075. Min Range: -6.7075
Max Act: 6.0200. Min Act: -0.1700
Data Index: 7632331 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7075. Min Range: -6.7075
Max Act: 5.9888. Min Act: -0.1700
Data Index: 7755166 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7075. Min Range: -6.7075
Max Act: 6.0200. Min Act: -0.1700
Data Index: 7843827 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7075. Min Range: -6.7075
Max Act: 6.0200. Min Act: -0.1700
Data Index: 3248639 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7075. Min Range: -6.7075
Max Act: 5.9888. Min Act: -0.1700
Data Index: 6839426 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7075. Min Range: -6.7075
Max Act: 5.9575. Min Act: -0.1700
Data Index: 1633008 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7075. Min Range: -6.7075
Max Act: 5.9888. Min Act: -0.1700
Data Index: 5089 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19