Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3286 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.2318. Min Range: -11.2318
Max Act: 11.2318. Min Act: -0.1700
Data Index: 2737599 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.2318. Min Range: -11.2318
Max Act: 11.2318. Min Act: -0.1700
Data Index: 5901192 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.2318. Min Range: -11.2318
Max Act: 11.0443. Min Act: -0.1700
Data Index: 3574961 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.2318. Min Range: -11.2318
Max Act: 10.9193. Min Act: -0.1700
Data Index: 917908 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.2318. Min Range: -11.2318
Max Act: 10.7943. Min Act: -0.1700
Data Index: 6208367 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.2318. Min Range: -11.2318
Max Act: 10.8568. Min Act: -0.1700
Data Index: 8210619 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.2318. Min Range: -11.2318
Max Act: 10.7943. Min Act: -0.1700
Data Index: 8048167 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.2318. Min Range: -11.2318
Max Act: 10.8568. Min Act: -0.1700
Data Index: 3121951 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.2318. Min Range: -11.2318
Max Act: 10.7943. Min Act: -0.1700
Data Index: 1157833 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.2318. Min Range: -11.2318
Max Act: 10.7318. Min Act: -0.1700
Data Index: 29540 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.2318. Min Range: -11.2318
Max Act: 10.6693. Min Act: -0.1700
Data Index: 1728952 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.2318. Min Range: -11.2318
Max Act: 10.6693. Min Act: -0.1700
Data Index: 4167399 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.2318. Min Range: -11.2318
Max Act: 10.6068. Min Act: -0.1700
Data Index: 5884760 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.2318. Min Range: -11.2318
Max Act: 10.5443. Min Act: -0.1700
Data Index: 5065253 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.2318. Min Range: -11.2318
Max Act: 10.5443. Min Act: -0.1700
Data Index: 5250238 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.2318. Min Range: -11.2318
Max Act: 10.4818. Min Act: -0.1700
Data Index: 2427076 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.2318. Min Range: -11.2318
Max Act: 10.4193. Min Act: -0.1700
Data Index: 2403518 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.2318. Min Range: -11.2318
Max Act: 10.4193. Min Act: -0.1700
Data Index: 5468458 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.2318. Min Range: -11.2318
Max Act: 10.2943. Min Act: -0.1700
Data Index: 7858305 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.2318. Min Range: -11.2318
Max Act: 10.3568. Min Act: -0.1700
Data Index: 5916785 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19