Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3569 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4277. Min Range: -8.4277
Max Act: 8.4277. Min Act: -0.1700
Data Index: 3586440 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4277. Min Range: -8.4277
Max Act: 8.3652. Min Act: -0.1700
Data Index: 6371694 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4277. Min Range: -8.4277
Max Act: 8.1152. Min Act: -0.1700
Data Index: 2915247 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4277. Min Range: -8.4277
Max Act: 8.0214. Min Act: -0.1700
Data Index: 5628246 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4277. Min Range: -8.4277
Max Act: 7.9902. Min Act: -0.1700
Data Index: 6309595 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4277. Min Range: -8.4277
Max Act: 7.8964. Min Act: -0.1700
Data Index: 4483437 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4277. Min Range: -8.4277
Max Act: 7.8652. Min Act: -0.1700
Data Index: 2734866 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4277. Min Range: -8.4277
Max Act: 7.8652. Min Act: -0.1700
Data Index: 3123815 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4277. Min Range: -8.4277
Max Act: 7.8652. Min Act: -0.1700
Data Index: 6114502 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4277. Min Range: -8.4277
Max Act: 7.8652. Min Act: -0.1700
Data Index: 3925480 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4277. Min Range: -8.4277
Max Act: 7.8339. Min Act: -0.1700
Data Index: 1615182 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4277. Min Range: -8.4277
Max Act: 7.8027. Min Act: -0.1700
Data Index: 5655953 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4277. Min Range: -8.4277
Max Act: 7.7714. Min Act: -0.1700
Data Index: 218572 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4277. Min Range: -8.4277
Max Act: 7.8027. Min Act: -0.1700
Data Index: 4626881 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4277. Min Range: -8.4277
Max Act: 7.7402. Min Act: -0.1700
Data Index: 8691342 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4277. Min Range: -8.4277
Max Act: 7.7714. Min Act: -0.1700
Data Index: 2795873 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4277. Min Range: -8.4277
Max Act: 7.8027. Min Act: -0.1700
Data Index: 2284423 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4277. Min Range: -8.4277
Max Act: 7.7402. Min Act: -0.1700
Data Index: 1238204 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4277. Min Range: -8.4277
Max Act: 7.7402. Min Act: -0.1700
Data Index: 1764560 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4277. Min Range: -8.4277
Max Act: 7.6777. Min Act: -0.1700
Data Index: 5224578 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19