Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3885 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3422. Min Range: -8.3422
Max Act: 8.2797. Min Act: -0.1700
Data Index: 7222988 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3422. Min Range: -8.3422
Max Act: 8.3422. Min Act: -0.1700
Data Index: 5120753 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3422. Min Range: -8.3422
Max Act: 8.2172. Min Act: -0.1700
Data Index: 518502 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3422. Min Range: -8.3422
Max Act: 7.7797. Min Act: -0.1700
Data Index: 2970742 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3422. Min Range: -8.3422
Max Act: 7.7172. Min Act: -0.1700
Data Index: 2847537 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3422. Min Range: -8.3422
Max Act: 7.7172. Min Act: -0.1700
Data Index: 1069975 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3422. Min Range: -8.3422
Max Act: 7.6547. Min Act: -0.1700
Data Index: 7900898 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3422. Min Range: -8.3422
Max Act: 7.6547. Min Act: -0.1700
Data Index: 5072143 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3422. Min Range: -8.3422
Max Act: 7.6547. Min Act: -0.1700
Data Index: 516529 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3422. Min Range: -8.3422
Max Act: 7.5922. Min Act: -0.1700
Data Index: 7466191 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3422. Min Range: -8.3422
Max Act: 7.5922. Min Act: -0.1700
Data Index: 875837 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3422. Min Range: -8.3422
Max Act: 7.5922. Min Act: -0.1700
Data Index: 7894509 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3422. Min Range: -8.3422
Max Act: 7.5922. Min Act: -0.1700
Data Index: 1742356 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3422. Min Range: -8.3422
Max Act: 7.5297. Min Act: -0.1700
Data Index: 2951355 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3422. Min Range: -8.3422
Max Act: 7.5297. Min Act: -0.1700
Data Index: 7652258 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3422. Min Range: -8.3422
Max Act: 7.5297. Min Act: -0.1700
Data Index: 4002960 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3422. Min Range: -8.3422
Max Act: 7.5297. Min Act: -0.1700
Data Index: 2709188 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3422. Min Range: -8.3422
Max Act: 7.4672. Min Act: -0.1700
Data Index: 4653298 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3422. Min Range: -8.3422
Max Act: 7.4672. Min Act: -0.1700
Data Index: 1756069 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3422. Min Range: -8.3422
Max Act: 7.4672. Min Act: -0.1700
Data Index: 6324770 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19