Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2894 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0154. Min Range: -7.0154
Max Act: 7.0154. Min Act: -0.1700
Data Index: 7035006 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0154. Min Range: -7.0154
Max Act: 6.8279. Min Act: -0.1700
Data Index: 6414527 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0154. Min Range: -7.0154
Max Act: 6.8279. Min Act: -0.1700
Data Index: 2534583 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0154. Min Range: -7.0154
Max Act: 6.7967. Min Act: -0.1700
Data Index: 1470680 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0154. Min Range: -7.0154
Max Act: 6.7029. Min Act: -0.1700
Data Index: 7303688 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0154. Min Range: -7.0154
Max Act: 6.6717. Min Act: -0.1700
Data Index: 6763489 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0154. Min Range: -7.0154
Max Act: 6.6092. Min Act: -0.1700
Data Index: 641644 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0154. Min Range: -7.0154
Max Act: 6.6092. Min Act: -0.1700
Data Index: 8740579 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0154. Min Range: -7.0154
Max Act: 6.6092. Min Act: -0.1700
Data Index: 428532 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0154. Min Range: -7.0154
Max Act: 6.5779. Min Act: -0.1700
Data Index: 7356296 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0154. Min Range: -7.0154
Max Act: 6.5467. Min Act: -0.1700
Data Index: 2993277 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0154. Min Range: -7.0154
Max Act: 6.5467. Min Act: -0.1700
Data Index: 4880933 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0154. Min Range: -7.0154
Max Act: 6.5467. Min Act: -0.1700
Data Index: 3271098 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0154. Min Range: -7.0154
Max Act: 6.5467. Min Act: -0.1700
Data Index: 1566876 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0154. Min Range: -7.0154
Max Act: 6.5467. Min Act: -0.1700
Data Index: 3881544 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0154. Min Range: -7.0154
Max Act: 6.4529. Min Act: -0.1700
Data Index: 803553 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0154. Min Range: -7.0154
Max Act: 6.4529. Min Act: -0.1700
Data Index: 2508565 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0154. Min Range: -7.0154
Max Act: 6.4529. Min Act: -0.1700
Data Index: 3208353 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0154. Min Range: -7.0154
Max Act: 6.3904. Min Act: -0.1700
Data Index: 7545356 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0154. Min Range: -7.0154
Max Act: 6.3592. Min Act: -0.1700
Data Index: 5521551 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19