Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3466 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.6011. Min Act: -0.1700
Data Index: 367097 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.5386. Min Act: -0.1700
Data Index: 5173195 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.4761. Min Act: -0.1700
Data Index: 3501991 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.4761. Min Act: -0.1700
Data Index: 4228719 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.4449. Min Act: -0.1700
Data Index: 992948 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.4136. Min Act: -0.1700
Data Index: 4817997 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.4136. Min Act: -0.1700
Data Index: 3655197 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.3824. Min Act: -0.1700
Data Index: 5116887 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.3199. Min Act: -0.1700
Data Index: 6083146 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.3199. Min Act: -0.1700
Data Index: 7811525 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.3199. Min Act: -0.1700
Data Index: 922676 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.2886. Min Act: -0.1700
Data Index: 507643 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.2261. Min Act: -0.1700
Data Index: 6879705 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.2261. Min Act: -0.1700
Data Index: 247855 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.2261. Min Act: -0.1700
Data Index: 7220064 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.2261. Min Act: -0.1700
Data Index: 7753601 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.1948. Min Act: -0.1700
Data Index: 8512286 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.2261. Min Act: -0.1700
Data Index: 5286705 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.1948. Min Act: -0.1700
Data Index: 4969152 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6011. Min Range: -4.6011
Max Act: 4.1948. Min Act: -0.1700
Data Index: 3861306 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19