Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2560 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4198. Min Range: -6.4198
Max Act: 6.4198. Min Act: -0.1700
Data Index: 5872629 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4198. Min Range: -6.4198
Max Act: 6.3573. Min Act: -0.1700
Data Index: 8751878 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4198. Min Range: -6.4198
Max Act: 6.2948. Min Act: -0.1700
Data Index: 3247117 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4198. Min Range: -6.4198
Max Act: 6.2948. Min Act: -0.1700
Data Index: 2623085 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4198. Min Range: -6.4198
Max Act: 6.2636. Min Act: -0.1700
Data Index: 4603770 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4198. Min Range: -6.4198
Max Act: 6.2011. Min Act: -0.1700
Data Index: 5753031 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4198. Min Range: -6.4198
Max Act: 6.2011. Min Act: -0.1700
Data Index: 8563035 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4198. Min Range: -6.4198
Max Act: 6.2011. Min Act: -0.1700
Data Index: 3441290 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4198. Min Range: -6.4198
Max Act: 6.1386. Min Act: -0.1700
Data Index: 4755686 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4198. Min Range: -6.4198
Max Act: 6.1386. Min Act: -0.1700
Data Index: 4986739 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4198. Min Range: -6.4198
Max Act: 6.0761. Min Act: -0.1700
Data Index: 615148 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4198. Min Range: -6.4198
Max Act: 6.0761. Min Act: -0.1700
Data Index: 8580615 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4198. Min Range: -6.4198
Max Act: 6.0761. Min Act: -0.1700
Data Index: 8751880 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4198. Min Range: -6.4198
Max Act: 6.0448. Min Act: -0.1700
Data Index: 2713584 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4198. Min Range: -6.4198
Max Act: 6.0448. Min Act: -0.1700
Data Index: 3364160 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4198. Min Range: -6.4198
Max Act: 6.0448. Min Act: -0.1700
Data Index: 5677839 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4198. Min Range: -6.4198
Max Act: 6.0136. Min Act: -0.1700
Data Index: 7040188 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4198. Min Range: -6.4198
Max Act: 6.0136. Min Act: -0.1700
Data Index: 7824923 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4198. Min Range: -6.4198
Max Act: 6.0136. Min Act: -0.1700
Data Index: 6180097 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4198. Min Range: -6.4198
Max Act: 5.9511. Min Act: -0.1700
Data Index: 1275773 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19