Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 856 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0240. Min Range: -5.0240
Max Act: 5.0240. Min Act: -0.1700
Data Index: 7154108 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0240. Min Range: -5.0240
Max Act: 4.9302. Min Act: -0.1700
Data Index: 4482338 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0240. Min Range: -5.0240
Max Act: 4.8990. Min Act: -0.1700
Data Index: 8271035 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0240. Min Range: -5.0240
Max Act: 4.8990. Min Act: -0.1700
Data Index: 7317921 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0240. Min Range: -5.0240
Max Act: 4.8365. Min Act: -0.1700
Data Index: 2004731 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0240. Min Range: -5.0240
Max Act: 4.8677. Min Act: -0.1700
Data Index: 824796 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0240. Min Range: -5.0240
Max Act: 4.8677. Min Act: -0.1700
Data Index: 6966990 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0240. Min Range: -5.0240
Max Act: 4.8052. Min Act: -0.1700
Data Index: 3186273 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0240. Min Range: -5.0240
Max Act: 4.8677. Min Act: -0.1700
Data Index: 4655857 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0240. Min Range: -5.0240
Max Act: 4.7740. Min Act: -0.1700
Data Index: 3551747 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0240. Min Range: -5.0240
Max Act: 4.8365. Min Act: -0.1700
Data Index: 6329373 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0240. Min Range: -5.0240
Max Act: 4.8052. Min Act: -0.1700
Data Index: 3559235 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0240. Min Range: -5.0240
Max Act: 4.8052. Min Act: -0.1700
Data Index: 3367698 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0240. Min Range: -5.0240
Max Act: 4.8052. Min Act: -0.1700
Data Index: 741702 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0240. Min Range: -5.0240
Max Act: 4.8052. Min Act: -0.1700
Data Index: 5754481 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0240. Min Range: -5.0240
Max Act: 4.8052. Min Act: -0.1700
Data Index: 4207919 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0240. Min Range: -5.0240
Max Act: 4.8052. Min Act: -0.1700
Data Index: 4237793 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0240. Min Range: -5.0240
Max Act: 4.8052. Min Act: -0.1700
Data Index: 2442641 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0240. Min Range: -5.0240
Max Act: 4.8052. Min Act: -0.1700
Data Index: 5573942 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0240. Min Range: -5.0240
Max Act: 4.7740. Min Act: -0.1700
Data Index: 7894671 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19