Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1926 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9845. Min Range: -7.9845
Max Act: 7.9845. Min Act: -0.1700
Data Index: 1089106 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9845. Min Range: -7.9845
Max Act: 7.9220. Min Act: -0.1700
Data Index: 8393710 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9845. Min Range: -7.9845
Max Act: 7.8595. Min Act: -0.1700
Data Index: 5256359 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9845. Min Range: -7.9845
Max Act: 7.7970. Min Act: -0.1700
Data Index: 8424608 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9845. Min Range: -7.9845
Max Act: 7.7970. Min Act: -0.1700
Data Index: 5256360 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9845. Min Range: -7.9845
Max Act: 7.7970. Min Act: -0.1700
Data Index: 2994077 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9845. Min Range: -7.9845
Max Act: 7.7345. Min Act: -0.1700
Data Index: 204606 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9845. Min Range: -7.9845
Max Act: 7.6095. Min Act: -0.1700
Data Index: 5772264 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9845. Min Range: -7.9845
Max Act: 7.5470. Min Act: -0.1700
Data Index: 4665221 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9845. Min Range: -7.9845
Max Act: 7.5470. Min Act: -0.1700
Data Index: 5922516 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9845. Min Range: -7.9845
Max Act: 7.5470. Min Act: -0.1700
Data Index: 6485787 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9845. Min Range: -7.9845
Max Act: 7.5158. Min Act: -0.1700
Data Index: 5847238 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9845. Min Range: -7.9845
Max Act: 7.4533. Min Act: -0.1700
Data Index: 5240207 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9845. Min Range: -7.9845
Max Act: 7.4845. Min Act: -0.1700
Data Index: 7076075 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9845. Min Range: -7.9845
Max Act: 7.4220. Min Act: -0.1700
Data Index: 7923090 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9845. Min Range: -7.9845
Max Act: 7.4220. Min Act: -0.1700
Data Index: 3285452 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9845. Min Range: -7.9845
Max Act: 7.3908. Min Act: -0.1700
Data Index: 3345298 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9845. Min Range: -7.9845
Max Act: 7.4220. Min Act: -0.1700
Data Index: 2620693 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9845. Min Range: -7.9845
Max Act: 7.3908. Min Act: -0.1700
Data Index: 4313846 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9845. Min Range: -7.9845
Max Act: 7.3908. Min Act: -0.1700
Data Index: 2155582 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19