Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2948 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4138. Min Range: -6.4138
Max Act: 6.4138. Min Act: -0.1700
Data Index: 7987992 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4138. Min Range: -6.4138
Max Act: 6.2263. Min Act: -0.1700
Data Index: 2259396 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4138. Min Range: -6.4138
Max Act: 6.1950. Min Act: -0.1700
Data Index: 11835 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4138. Min Range: -6.4138
Max Act: 6.1013. Min Act: -0.1700
Data Index: 8391898 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4138. Min Range: -6.4138
Max Act: 6.0700. Min Act: -0.1700
Data Index: 311217 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4138. Min Range: -6.4138
Max Act: 6.0700. Min Act: -0.1700
Data Index: 5496552 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4138. Min Range: -6.4138
Max Act: 6.0700. Min Act: -0.1700
Data Index: 8392265 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4138. Min Range: -6.4138
Max Act: 6.0388. Min Act: -0.1700
Data Index: 1573904 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4138. Min Range: -6.4138
Max Act: 6.0388. Min Act: -0.1700
Data Index: 2857075 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4138. Min Range: -6.4138
Max Act: 6.0075. Min Act: -0.1700
Data Index: 7601509 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4138. Min Range: -6.4138
Max Act: 6.0075. Min Act: -0.1700
Data Index: 5085615 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4138. Min Range: -6.4138
Max Act: 5.9763. Min Act: -0.1700
Data Index: 100769 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4138. Min Range: -6.4138
Max Act: 5.9763. Min Act: -0.1700
Data Index: 2259397 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4138. Min Range: -6.4138
Max Act: 5.9763. Min Act: -0.1700
Data Index: 6708138 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4138. Min Range: -6.4138
Max Act: 5.9450. Min Act: -0.1700
Data Index: 6146641 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4138. Min Range: -6.4138
Max Act: 5.8825. Min Act: -0.1700
Data Index: 6656282 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4138. Min Range: -6.4138
Max Act: 5.8825. Min Act: -0.1700
Data Index: 1578255 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4138. Min Range: -6.4138
Max Act: 5.9138. Min Act: -0.1700
Data Index: 8392268 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4138. Min Range: -6.4138
Max Act: 5.9138. Min Act: -0.1700
Data Index: 4875628 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4138. Min Range: -6.4138
Max Act: 5.8825. Min Act: -0.1700
Data Index: 5711536 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19