Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1525 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2776. Min Range: -2.2776
Max Act: 2.2776. Min Act: -0.1700
Data Index: 2765199 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2776. Min Range: -2.2776
Max Act: 2.1449. Min Act: -0.1700
Data Index: 4155838 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2776. Min Range: -2.2776
Max Act: 2.1282. Min Act: -0.1700
Data Index: 3696099 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2776. Min Range: -2.2776
Max Act: 2.0948. Min Act: -0.1700
Data Index: 5956697 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2776. Min Range: -2.2776
Max Act: 2.1115. Min Act: -0.1700
Data Index: 1104367 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2776. Min Range: -2.2776
Max Act: 2.0948. Min Act: -0.1700
Data Index: 6227004 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2776. Min Range: -2.2776
Max Act: 2.0780. Min Act: -0.1700
Data Index: 5499605 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2776. Min Range: -2.2776
Max Act: 2.0780. Min Act: -0.1700
Data Index: 7433151 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2776. Min Range: -2.2776
Max Act: 2.0948. Min Act: -0.1700
Data Index: 7944168 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2776. Min Range: -2.2776
Max Act: 2.0948. Min Act: -0.1700
Data Index: 7404618 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2776. Min Range: -2.2776
Max Act: 2.0948. Min Act: -0.1700
Data Index: 7136677 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2776. Min Range: -2.2776
Max Act: 2.0948. Min Act: -0.1700
Data Index: 1460094 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2776. Min Range: -2.2776
Max Act: 2.0948. Min Act: -0.1700
Data Index: 6989479 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2776. Min Range: -2.2776
Max Act: 2.0948. Min Act: -0.1700
Data Index: 6328920 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2776. Min Range: -2.2776
Max Act: 2.0780. Min Act: -0.1700
Data Index: 7317044 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2776. Min Range: -2.2776
Max Act: 2.0948. Min Act: -0.1700
Data Index: 1964611 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2776. Min Range: -2.2776
Max Act: 2.0612. Min Act: -0.1700
Data Index: 841624 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2776. Min Range: -2.2776
Max Act: 2.0612. Min Act: -0.1700
Data Index: 5392324 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2776. Min Range: -2.2776
Max Act: 2.0612. Min Act: -0.1700
Data Index: 2819998 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2776. Min Range: -2.2776
Max Act: 2.0612. Min Act: -0.1700
Data Index: 7589173 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19