Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3055 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.8761. Min Act: -0.1700
Data Index: 6556080 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.6886. Min Act: -0.1700
Data Index: 1218148 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.5636. Min Act: -0.1700
Data Index: 4952186 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.5323. Min Act: -0.1700
Data Index: 4880982 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.5011. Min Act: -0.1700
Data Index: 4527741 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.5011. Min Act: -0.1700
Data Index: 3187324 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.5011. Min Act: -0.1700
Data Index: 7316725 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.4698. Min Act: -0.1700
Data Index: 8758305 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.4698. Min Act: -0.1700
Data Index: 1069818 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.4386. Min Act: -0.1700
Data Index: 472690 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.3448. Min Act: -0.1700
Data Index: 5780481 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.3448. Min Act: -0.1700
Data Index: 6017396 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.3448. Min Act: -0.1700
Data Index: 2020283 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.3136. Min Act: -0.1700
Data Index: 3541484 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.3448. Min Act: -0.1700
Data Index: 4666910 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.3448. Min Act: -0.1700
Data Index: 2477776 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.2823. Min Act: -0.1700
Data Index: 2242196 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.2823. Min Act: -0.1700
Data Index: 1081802 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.2823. Min Act: -0.1700
Data Index: 2945579 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8761. Min Range: -5.8761
Max Act: 5.2823. Min Act: -0.1700
Data Index: 4702334 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #19