Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3074 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.5069. Min Act: -0.1700
Data Index: 278838 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.2881. Min Act: -0.1700
Data Index: 2064741 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.2881. Min Act: -0.1700
Data Index: 8262136 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.2881. Min Act: -0.1700
Data Index: 6208425 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.2881. Min Act: -0.1700
Data Index: 2567295 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.2569. Min Act: -0.1700
Data Index: 5020721 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.2569. Min Act: -0.1700
Data Index: 8050407 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.2256. Min Act: -0.1700
Data Index: 5597099 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.2569. Min Act: -0.1700
Data Index: 3071979 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.2256. Min Act: -0.1700
Data Index: 3992449 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.2256. Min Act: -0.1700
Data Index: 4953843 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.2256. Min Act: -0.1700
Data Index: 7926425 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.1944. Min Act: -0.1700
Data Index: 3736420 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.1944. Min Act: -0.1700
Data Index: 1125051 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.1631. Min Act: -0.1700
Data Index: 7651565 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.1944. Min Act: -0.1700
Data Index: 1427084 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.1944. Min Act: -0.1700
Data Index: 1066958 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.1944. Min Act: -0.1700
Data Index: 5784002 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.1944. Min Act: -0.1700
Data Index: 4953844 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.1944. Min Act: -0.1700
Data Index: 2229413 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19