Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2904 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0791. Min Range: -5.0791
Max Act: 5.0791. Min Act: -0.1700
Data Index: 329373 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0791. Min Range: -5.0791
Max Act: 5.0166. Min Act: -0.1700
Data Index: 4538146 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0791. Min Range: -5.0791
Max Act: 4.9853. Min Act: -0.1700
Data Index: 7076374 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0791. Min Range: -5.0791
Max Act: 4.9853. Min Act: -0.1700
Data Index: 8418969 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0791. Min Range: -5.0791
Max Act: 4.9541. Min Act: -0.1700
Data Index: 1882050 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0791. Min Range: -5.0791
Max Act: 4.9228. Min Act: -0.1700
Data Index: 6808031 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0791. Min Range: -5.0791
Max Act: 4.9541. Min Act: -0.1700
Data Index: 2506540 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0791. Min Range: -5.0791
Max Act: 4.9541. Min Act: -0.1700
Data Index: 1783448 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0791. Min Range: -5.0791
Max Act: 4.9541. Min Act: -0.1700
Data Index: 4642204 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0791. Min Range: -5.0791
Max Act: 4.9541. Min Act: -0.1700
Data Index: 3992481 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0791. Min Range: -5.0791
Max Act: 4.9541. Min Act: -0.1700
Data Index: 705250 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0791. Min Range: -5.0791
Max Act: 4.9228. Min Act: -0.1699
Data Index: 2978036 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0791. Min Range: -5.0791
Max Act: 4.9541. Min Act: -0.1700
Data Index: 8041658 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0791. Min Range: -5.0791
Max Act: 4.8916. Min Act: -0.1700
Data Index: 16189 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0791. Min Range: -5.0791
Max Act: 4.9228. Min Act: -0.1700
Data Index: 2115118 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0791. Min Range: -5.0791
Max Act: 4.9228. Min Act: -0.1700
Data Index: 4740689 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0791. Min Range: -5.0791
Max Act: 4.9228. Min Act: -0.1700
Data Index: 4932121 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0791. Min Range: -5.0791
Max Act: 4.8916. Min Act: -0.1700
Data Index: 2270642 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0791. Min Range: -5.0791
Max Act: 4.8916. Min Act: -0.1700
Data Index: 5277272 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0791. Min Range: -5.0791
Max Act: 4.8916. Min Act: -0.1700
Data Index: 2432946 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19