Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3639 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5450. Min Range: -5.5450
Max Act: 5.5450. Min Act: -0.1700
Data Index: 482176 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5450. Min Range: -5.5450
Max Act: 5.0450. Min Act: -0.1700
Data Index: 3053202 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5450. Min Range: -5.5450
Max Act: 4.7325. Min Act: -0.1700
Data Index: 8449001 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5450. Min Range: -5.5450
Max Act: 4.6700. Min Act: -0.1700
Data Index: 8008526 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5450. Min Range: -5.5450
Max Act: 4.6700. Min Act: -0.1700
Data Index: 2189075 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5450. Min Range: -5.5450
Max Act: 4.6075. Min Act: -0.1700
Data Index: 3677850 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5450. Min Range: -5.5450
Max Act: 4.6075. Min Act: -0.1700
Data Index: 274564 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5450. Min Range: -5.5450
Max Act: 4.6075. Min Act: -0.1700
Data Index: 5758954 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5450. Min Range: -5.5450
Max Act: 4.5763. Min Act: -0.1700
Data Index: 3303584 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5450. Min Range: -5.5450
Max Act: 4.5763. Min Act: -0.1700
Data Index: 179648 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5450. Min Range: -5.5450
Max Act: 4.5138. Min Act: -0.1700
Data Index: 8762284 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5450. Min Range: -5.5450
Max Act: 4.5450. Min Act: -0.1700
Data Index: 4254717 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5450. Min Range: -5.5450
Max Act: 4.5138. Min Act: -0.1700
Data Index: 3192651 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5450. Min Range: -5.5450
Max Act: 4.5138. Min Act: -0.1700
Data Index: 1117115 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5450. Min Range: -5.5450
Max Act: 4.4825. Min Act: -0.1700
Data Index: 1694205 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5450. Min Range: -5.5450
Max Act: 4.5138. Min Act: -0.1700
Data Index: 8369598 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5450. Min Range: -5.5450
Max Act: 4.4825. Min Act: -0.1700
Data Index: 4630206 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5450. Min Range: -5.5450
Max Act: 4.4825. Min Act: -0.1700
Data Index: 4558481 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5450. Min Range: -5.5450
Max Act: 4.4825. Min Act: -0.1700
Data Index: 684828 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5450. Min Range: -5.5450
Max Act: 4.4825. Min Act: -0.1700
Data Index: 2521275 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #19